├── .gitignore ├── LEGAL.md ├── LICENSE ├── README.md ├── demo ├── central_cloud.py ├── edge_device.py ├── model.py ├── pl_lib.py ├── prepare_weights.py └── readme.md ├── doc └── figs │ ├── demo_gen.gif │ └── privatelora.png ├── experiments ├── .DS_Store ├── __init__.py ├── baseline_lora_config.py ├── exp_private_lora.py ├── infras │ ├── __init__.py │ ├── arguments.py │ ├── data.py │ ├── eval.py │ ├── model_utils.py │ └── open_bench.py ├── mymodels │ └── modeling_llama_pl.py ├── new_ds_config.json ├── readme.md └── scripts │ ├── baseline.sh │ └── pl.sh └── lm-evaluation-harness ├── .coveragerc ├── .flake8 ├── .gitignore ├── .pre-commit-config.yaml ├── CITATION.bib ├── CODEOWNERS ├── LICENSE.md ├── README.md ├── docs ├── README.md ├── decontamination.md ├── img │ └── fewshot_example_gpt3.png ├── interface.md ├── model_guide.md ├── new_task_guide.md └── task_guide.md ├── examples ├── README.md └── chain_of_thought │ └── README.md ├── ignore.txt ├── lm_eval ├── __init__.py ├── __main__.py ├── api │ ├── __init__.py │ ├── filter.py │ ├── instance.py │ ├── metrics.py │ ├── model.py │ ├── registry.py │ ├── samplers.py │ └── task.py ├── benchmarks │ ├── __init__.py │ └── minerva_math.yaml ├── decontamination │ ├── __init__.py │ ├── archiver.py │ ├── decontaminate.py │ └── janitor.py ├── evaluator.py ├── filters │ ├── __init__.py │ ├── decontamination.py │ ├── extraction.py │ ├── selection.py │ └── transformation.py ├── logger.py ├── models │ ├── __init__.py │ ├── anthropic_llms.py │ ├── dummy.py │ ├── huggingface.py │ ├── openai_completions.py │ └── textsynth.py ├── prompts │ └── __init__.py ├── tasks │ ├── README.md │ ├── __init__.py │ ├── anli │ │ ├── README.md │ │ ├── anli_r1.yaml │ │ ├── anli_r2.yaml │ │ └── anli_r3.yaml │ ├── arc │ │ ├── README.md │ │ ├── arc_challenge.yaml │ │ └── arc_easy.yaml │ ├── arithmetic │ │ ├── README.md │ │ ├── arithmetic_1dc.yaml │ │ ├── arithmetic_2da.yaml │ │ ├── arithmetic_2dm.yaml │ │ ├── arithmetic_2ds.yaml │ │ ├── arithmetic_3da.yaml │ │ ├── arithmetic_3ds.yaml │ │ ├── arithmetic_4da.yaml │ │ ├── arithmetic_4ds.yaml │ │ ├── arithmetic_5da.yaml │ │ └── arithmetic_5ds.yaml │ ├── asdiv │ │ ├── README.md │ │ └── default.yaml │ ├── babi │ │ ├── README.md │ │ └── babi.yaml │ ├── bbh │ │ ├── README.md │ │ ├── _generate_configs.py │ │ ├── flan_cot_fewshot │ │ │ ├── _flan_cot_fewshot_template_yaml │ │ │ ├── boolean_expressions.yaml │ │ │ ├── causal_judgement.yaml │ │ │ ├── date_understanding.yaml │ │ │ ├── disambiguation_qa.yaml │ │ │ ├── dyck_languages.yaml │ │ │ ├── formal_fallacies.yaml │ │ │ ├── geometric_shapes.yaml │ │ │ ├── hyperbaton.yaml │ │ │ ├── logical_deduction_five_objects.yaml │ │ │ ├── logical_deduction_seven_objects.yaml │ │ │ ├── logical_deduction_three_objects.yaml │ │ │ ├── movie_recommendation.yaml │ │ │ ├── multistep_arithmetic_two.yaml │ │ │ ├── navigate.yaml │ │ │ ├── object_counting.yaml │ │ │ ├── penguins_in_a_table.yaml │ │ │ ├── reasoning_about_colored_objects.yaml │ │ │ ├── ruin_names.yaml │ │ │ ├── salient_translation_error_detection.yaml │ │ │ ├── snarks.yaml │ │ │ ├── sports_understanding.yaml │ │ │ ├── temporal_sequences.yaml │ │ │ ├── tracking_shuffled_objects_five_objects.yaml │ │ │ ├── tracking_shuffled_objects_seven_objects.yaml │ │ │ ├── tracking_shuffled_objects_three_objects.yaml │ │ │ ├── web_of_lies.yaml │ │ │ └── word_sorting.yaml │ │ ├── flan_cot_zeroshot │ │ │ ├── _flan_cot_zeroshot_template_yaml │ │ │ ├── boolean_expressions.yaml │ │ │ ├── causal_judgement.yaml │ │ │ ├── date_understanding.yaml │ │ │ ├── disambiguation_qa.yaml │ │ │ ├── dyck_languages.yaml │ │ │ ├── formal_fallacies.yaml │ │ │ ├── geometric_shapes.yaml │ │ │ ├── hyperbaton.yaml │ │ │ ├── logical_deduction_five_objects.yaml │ │ │ ├── logical_deduction_seven_objects.yaml │ │ │ ├── logical_deduction_three_objects.yaml │ │ │ ├── movie_recommendation.yaml │ │ │ ├── multistep_arithmetic_two.yaml │ │ │ ├── navigate.yaml │ │ │ ├── object_counting.yaml │ │ │ ├── penguins_in_a_table.yaml │ │ │ ├── reasoning_about_colored_objects.yaml │ │ │ ├── ruin_names.yaml │ │ │ ├── salient_translation_error_detection.yaml │ │ │ ├── snarks.yaml │ │ │ ├── sports_understanding.yaml │ │ │ ├── temporal_sequences.yaml │ │ │ ├── tracking_shuffled_objects_five_objects.yaml │ │ │ ├── tracking_shuffled_objects_seven_objects.yaml │ │ │ ├── tracking_shuffled_objects_three_objects.yaml │ │ │ ├── web_of_lies.yaml │ │ │ └── word_sorting.yaml │ │ ├── flan_fewshot │ │ │ ├── _flan_fewshot_template_yaml │ │ │ ├── boolean_expressions.yaml │ │ │ ├── causal_judgement.yaml │ │ │ ├── date_understanding.yaml │ │ │ ├── disambiguation_qa.yaml │ │ │ ├── dyck_languages.yaml │ │ │ ├── formal_fallacies.yaml │ │ │ ├── geometric_shapes.yaml │ │ │ ├── hyperbaton.yaml │ │ │ ├── logical_deduction_five_objects.yaml │ │ │ ├── logical_deduction_seven_objects.yaml │ │ │ ├── logical_deduction_three_objects.yaml │ │ │ ├── movie_recommendation.yaml │ │ │ ├── multistep_arithmetic_two.yaml │ │ │ ├── navigate.yaml │ │ │ ├── object_counting.yaml │ │ │ ├── penguins_in_a_table.yaml │ │ │ ├── reasoning_about_colored_objects.yaml │ │ │ ├── ruin_names.yaml │ │ │ ├── salient_translation_error_detection.yaml │ │ │ ├── snarks.yaml │ │ │ ├── sports_understanding.yaml │ │ │ ├── temporal_sequences.yaml │ │ │ ├── tracking_shuffled_objects_five_objects.yaml │ │ │ ├── tracking_shuffled_objects_seven_objects.yaml │ │ │ ├── tracking_shuffled_objects_three_objects.yaml │ │ │ ├── web_of_lies.yaml │ │ │ └── word_sorting.yaml │ │ └── flan_zeroshot │ │ │ ├── _flan_zeroshot_template_yaml │ │ │ ├── boolean_expressions.yaml │ │ │ ├── causal_judgement.yaml │ │ │ ├── date_understanding.yaml │ │ │ ├── disambiguation_qa.yaml │ │ │ ├── dyck_languages.yaml │ │ │ ├── formal_fallacies.yaml │ │ │ ├── geometric_shapes.yaml │ │ │ ├── hyperbaton.yaml │ │ │ ├── logical_deduction_five_objects.yaml │ │ │ ├── logical_deduction_seven_objects.yaml │ │ │ ├── logical_deduction_three_objects.yaml │ │ │ ├── movie_recommendation.yaml │ │ │ ├── multistep_arithmetic_two.yaml │ │ │ ├── navigate.yaml │ │ │ ├── object_counting.yaml │ │ │ ├── penguins_in_a_table.yaml │ │ │ ├── reasoning_about_colored_objects.yaml │ │ │ ├── ruin_names.yaml │ │ │ ├── salient_translation_error_detection.yaml │ │ │ ├── snarks.yaml │ │ │ ├── sports_understanding.yaml │ │ │ ├── temporal_sequences.yaml │ │ │ ├── tracking_shuffled_objects_five_objects.yaml │ │ │ ├── tracking_shuffled_objects_seven_objects.yaml │ │ │ ├── tracking_shuffled_objects_three_objects.yaml │ │ │ ├── web_of_lies.yaml │ │ │ └── word_sorting.yaml │ ├── benchmarks │ │ ├── flan │ │ │ ├── flan_anli.yaml │ │ │ ├── flan_arc.yaml │ │ │ ├── flan_boolq.yaml │ │ │ ├── flan_cot.yaml │ │ │ ├── flan_held_in.yaml │ │ │ ├── flan_held_in_yaml │ │ │ ├── flan_held_out.yaml │ │ │ ├── flan_rte.yaml │ │ │ ├── prompt_templates │ │ │ │ ├── anli.yaml │ │ │ │ ├── arc.yaml │ │ │ │ ├── boolq.yaml │ │ │ │ └── rte.yaml │ │ │ └── yaml_templates │ │ │ │ ├── cot_template_yaml │ │ │ │ └── held_in_template_yaml │ │ ├── pythia.yaml │ │ └── t0_eval.yaml │ ├── bigbench │ │ ├── README.md │ │ ├── generate_tasks.py │ │ ├── greedy_until │ │ │ ├── abstract_narrative_understanding.yaml │ │ │ ├── anachronisms.yaml │ │ │ ├── analogical_similarity.yaml │ │ │ ├── analytic_entailment.yaml │ │ │ ├── arithmetic.yaml │ │ │ ├── ascii_word_recognition.yaml │ │ │ ├── authorship_verification.yaml │ │ │ ├── auto_categorization.yaml │ │ │ ├── auto_debugging.yaml │ │ │ ├── bbq_lite_json.yaml │ │ │ ├── bridging_anaphora_resolution_barqa.yaml │ │ │ ├── causal_judgment.yaml │ │ │ ├── cause_and_effect.yaml │ │ │ ├── checkmate_in_one.yaml │ │ │ ├── chess_state_tracking.yaml │ │ │ ├── chinese_remainder_theorem.yaml │ │ │ ├── cifar10_classification.yaml │ │ │ ├── code_line_description.yaml │ │ │ ├── codenames.yaml │ │ │ ├── color.yaml │ │ │ ├── common_morpheme.yaml │ │ │ ├── conceptual_combinations.yaml │ │ │ ├── conlang_translation.yaml │ │ │ ├── contextual_parametric_knowledge_conflicts.yaml │ │ │ ├── crash_blossom.yaml │ │ │ ├── crass_ai.yaml │ │ │ ├── cryobiology_spanish.yaml │ │ │ ├── cryptonite.yaml │ │ │ ├── cs_algorithms.yaml │ │ │ ├── dark_humor_detection.yaml │ │ │ ├── date_understanding.yaml │ │ │ ├── disambiguation_qa.yaml │ │ │ ├── discourse_marker_prediction.yaml │ │ │ ├── disfl_qa.yaml │ │ │ ├── dyck_languages.yaml │ │ │ ├── elementary_math_qa.yaml │ │ │ ├── emoji_movie.yaml │ │ │ ├── emojis_emotion_prediction.yaml │ │ │ ├── empirical_judgments.yaml │ │ │ ├── english_proverbs.yaml │ │ │ ├── english_russian_proverbs.yaml │ │ │ ├── entailed_polarity.yaml │ │ │ ├── entailed_polarity_hindi.yaml │ │ │ ├── epistemic_reasoning.yaml │ │ │ ├── evaluating_information_essentiality.yaml │ │ │ ├── fact_checker.yaml │ │ │ ├── fantasy_reasoning.yaml │ │ │ ├── few_shot_nlg.yaml │ │ │ ├── figure_of_speech_detection.yaml │ │ │ ├── formal_fallacies_syllogisms_negation.yaml │ │ │ ├── gem.yaml │ │ │ ├── gender_inclusive_sentences_german.yaml │ │ │ ├── general_knowledge.yaml │ │ │ ├── geometric_shapes.yaml │ │ │ ├── goal_step_wikihow.yaml │ │ │ ├── gre_reading_comprehension.yaml │ │ │ ├── hhh_alignment.yaml │ │ │ ├── hindi_question_answering.yaml │ │ │ ├── hindu_knowledge.yaml │ │ │ ├── hinglish_toxicity.yaml │ │ │ ├── human_organs_senses.yaml │ │ │ ├── hyperbaton.yaml │ │ │ ├── identify_math_theorems.yaml │ │ │ ├── identify_odd_metaphor.yaml │ │ │ ├── implicatures.yaml │ │ │ ├── implicit_relations.yaml │ │ │ ├── intent_recognition.yaml │ │ │ ├── international_phonetic_alphabet_nli.yaml │ │ │ ├── international_phonetic_alphabet_transliterate.yaml │ │ │ ├── intersect_geometry.yaml │ │ │ ├── irony_identification.yaml │ │ │ ├── kanji_ascii.yaml │ │ │ ├── kannada.yaml │ │ │ ├── key_value_maps.yaml │ │ │ ├── known_unknowns.yaml │ │ │ ├── language_games.yaml │ │ │ ├── language_identification.yaml │ │ │ ├── linguistic_mappings.yaml │ │ │ ├── linguistics_puzzles.yaml │ │ │ ├── list_functions.yaml │ │ │ ├── logic_grid_puzzle.yaml │ │ │ ├── logical_args.yaml │ │ │ ├── logical_deduction.yaml │ │ │ ├── logical_fallacy_detection.yaml │ │ │ ├── logical_sequence.yaml │ │ │ ├── mathematical_induction.yaml │ │ │ ├── matrixshapes.yaml │ │ │ ├── metaphor_boolean.yaml │ │ │ ├── metaphor_understanding.yaml │ │ │ ├── minute_mysteries_qa.yaml │ │ │ ├── misconceptions.yaml │ │ │ ├── misconceptions_russian.yaml │ │ │ ├── mnist_ascii.yaml │ │ │ ├── modified_arithmetic.yaml │ │ │ ├── moral_permissibility.yaml │ │ │ ├── movie_dialog_same_or_different.yaml │ │ │ ├── movie_recommendation.yaml │ │ │ ├── mult_data_wrangling.yaml │ │ │ ├── multiemo.yaml │ │ │ ├── natural_instructions.yaml │ │ │ ├── navigate.yaml │ │ │ ├── nonsense_words_grammar.yaml │ │ │ ├── novel_concepts.yaml │ │ │ ├── object_counting.yaml │ │ │ ├── odd_one_out.yaml │ │ │ ├── operators.yaml │ │ │ ├── paragraph_segmentation.yaml │ │ │ ├── parsinlu_qa.yaml │ │ │ ├── parsinlu_reading_comprehension.yaml │ │ │ ├── penguins_in_a_table.yaml │ │ │ ├── periodic_elements.yaml │ │ │ ├── persian_idioms.yaml │ │ │ ├── phrase_relatedness.yaml │ │ │ ├── physical_intuition.yaml │ │ │ ├── physics.yaml │ │ │ ├── physics_questions.yaml │ │ │ ├── play_dialog_same_or_different.yaml │ │ │ ├── polish_sequence_labeling.yaml │ │ │ ├── presuppositions_as_nli.yaml │ │ │ ├── qa_wikidata.yaml │ │ │ ├── question_selection.yaml │ │ │ ├── real_or_fake_text.yaml │ │ │ ├── reasoning_about_colored_objects.yaml │ │ │ ├── repeat_copy_logic.yaml │ │ │ ├── rephrase.yaml │ │ │ ├── riddle_sense.yaml │ │ │ ├── ruin_names.yaml │ │ │ ├── salient_translation_error_detection.yaml │ │ │ ├── scientific_press_release.yaml │ │ │ ├── semantic_parsing_in_context_sparc.yaml │ │ │ ├── semantic_parsing_spider.yaml │ │ │ ├── sentence_ambiguity.yaml │ │ │ ├── similarities_abstraction.yaml │ │ │ ├── simp_turing_concept.yaml │ │ │ ├── simple_arithmetic_json.yaml │ │ │ ├── simple_arithmetic_json_multiple_choice.yaml │ │ │ ├── simple_arithmetic_json_subtasks.yaml │ │ │ ├── simple_arithmetic_multiple_targets_json.yaml │ │ │ ├── simple_ethical_questions.yaml │ │ │ ├── simple_text_editing.yaml │ │ │ ├── snarks.yaml │ │ │ ├── social_iqa.yaml │ │ │ ├── social_support.yaml │ │ │ ├── sports_understanding.yaml │ │ │ ├── strange_stories.yaml │ │ │ ├── strategyqa.yaml │ │ │ ├── sufficient_information.yaml │ │ │ ├── suicide_risk.yaml │ │ │ ├── swahili_english_proverbs.yaml │ │ │ ├── swedish_to_german_proverbs.yaml │ │ │ ├── symbol_interpretation.yaml │ │ │ ├── temporal_sequences.yaml │ │ │ ├── tense.yaml │ │ │ ├── timedial.yaml │ │ │ ├── topical_chat.yaml │ │ │ ├── tracking_shuffled_objects.yaml │ │ │ ├── understanding_fables.yaml │ │ │ ├── undo_permutation.yaml │ │ │ ├── unit_conversion.yaml │ │ │ ├── unit_interpretation.yaml │ │ │ ├── unnatural_in_context_learning.yaml │ │ │ ├── vitaminc_fact_verification.yaml │ │ │ ├── what_is_the_tao.yaml │ │ │ ├── which_wiki_edit.yaml │ │ │ ├── winowhy.yaml │ │ │ ├── word_sorting.yaml │ │ │ └── word_unscrambling.yaml │ │ ├── greedy_until_template_yaml │ │ ├── multiple_choice │ │ │ ├── abstract_narrative_understanding.yaml │ │ │ ├── anachronisms.yaml │ │ │ ├── analogical_similarity.yaml │ │ │ ├── analytic_entailment.yaml │ │ │ ├── arithmetic.yaml │ │ │ ├── ascii_word_recognition.yaml │ │ │ ├── authorship_verification.yaml │ │ │ ├── auto_categorization.yaml │ │ │ ├── auto_debugging.yaml │ │ │ ├── bbq_lite_json.yaml │ │ │ ├── bridging_anaphora_resolution_barqa.yaml │ │ │ ├── causal_judgment.yaml │ │ │ ├── cause_and_effect.yaml │ │ │ ├── checkmate_in_one.yaml │ │ │ ├── chess_state_tracking.yaml │ │ │ ├── chinese_remainder_theorem.yaml │ │ │ ├── cifar10_classification.yaml │ │ │ ├── code_line_description.yaml │ │ │ ├── codenames.yaml │ │ │ ├── color.yaml │ │ │ ├── common_morpheme.yaml │ │ │ ├── conceptual_combinations.yaml │ │ │ ├── conlang_translation.yaml │ │ │ ├── contextual_parametric_knowledge_conflicts.yaml │ │ │ ├── crash_blossom.yaml │ │ │ ├── crass_ai.yaml │ │ │ ├── cryobiology_spanish.yaml │ │ │ ├── cryptonite.yaml │ │ │ ├── cs_algorithms.yaml │ │ │ ├── dark_humor_detection.yaml │ │ │ ├── date_understanding.yaml │ │ │ ├── disambiguation_qa.yaml │ │ │ ├── discourse_marker_prediction.yaml │ │ │ ├── disfl_qa.yaml │ │ │ ├── dyck_languages.yaml │ │ │ ├── elementary_math_qa.yaml │ │ │ ├── emoji_movie.yaml │ │ │ ├── emojis_emotion_prediction.yaml │ │ │ ├── empirical_judgments.yaml │ │ │ ├── english_proverbs.yaml │ │ │ ├── english_russian_proverbs.yaml │ │ │ ├── entailed_polarity.yaml │ │ │ ├── entailed_polarity_hindi.yaml │ │ │ ├── epistemic_reasoning.yaml │ │ │ ├── evaluating_information_essentiality.yaml │ │ │ ├── fact_checker.yaml │ │ │ ├── fantasy_reasoning.yaml │ │ │ ├── few_shot_nlg.yaml │ │ │ ├── figure_of_speech_detection.yaml │ │ │ ├── formal_fallacies_syllogisms_negation.yaml │ │ │ ├── gem.yaml │ │ │ ├── gender_inclusive_sentences_german.yaml │ │ │ ├── general_knowledge.yaml │ │ │ ├── geometric_shapes.yaml │ │ │ ├── goal_step_wikihow.yaml │ │ │ ├── gre_reading_comprehension.yaml │ │ │ ├── hhh_alignment.yaml │ │ │ ├── hindi_question_answering.yaml │ │ │ ├── hindu_knowledge.yaml │ │ │ ├── hinglish_toxicity.yaml │ │ │ ├── human_organs_senses.yaml │ │ │ ├── hyperbaton.yaml │ │ │ ├── identify_math_theorems.yaml │ │ │ ├── identify_odd_metaphor.yaml │ │ │ ├── implicatures.yaml │ │ │ ├── implicit_relations.yaml │ │ │ ├── intent_recognition.yaml │ │ │ ├── international_phonetic_alphabet_nli.yaml │ │ │ ├── international_phonetic_alphabet_transliterate.yaml │ │ │ ├── intersect_geometry.yaml │ │ │ ├── irony_identification.yaml │ │ │ ├── kanji_ascii.yaml │ │ │ ├── kannada.yaml │ │ │ ├── key_value_maps.yaml │ │ │ ├── known_unknowns.yaml │ │ │ ├── language_games.yaml │ │ │ ├── language_identification.yaml │ │ │ ├── linguistic_mappings.yaml │ │ │ ├── linguistics_puzzles.yaml │ │ │ ├── list_functions.yaml │ │ │ ├── logic_grid_puzzle.yaml │ │ │ ├── logical_args.yaml │ │ │ ├── logical_deduction.yaml │ │ │ ├── logical_fallacy_detection.yaml │ │ │ ├── logical_sequence.yaml │ │ │ ├── mathematical_induction.yaml │ │ │ ├── matrixshapes.yaml │ │ │ ├── metaphor_boolean.yaml │ │ │ ├── metaphor_understanding.yaml │ │ │ ├── minute_mysteries_qa.yaml │ │ │ ├── misconceptions.yaml │ │ │ ├── misconceptions_russian.yaml │ │ │ ├── mnist_ascii.yaml │ │ │ ├── modified_arithmetic.yaml │ │ │ ├── moral_permissibility.yaml │ │ │ ├── movie_dialog_same_or_different.yaml │ │ │ ├── movie_recommendation.yaml │ │ │ ├── mult_data_wrangling.yaml │ │ │ ├── multiemo.yaml │ │ │ ├── natural_instructions.yaml │ │ │ ├── navigate.yaml │ │ │ ├── nonsense_words_grammar.yaml │ │ │ ├── novel_concepts.yaml │ │ │ ├── object_counting.yaml │ │ │ ├── odd_one_out.yaml │ │ │ ├── operators.yaml │ │ │ ├── paragraph_segmentation.yaml │ │ │ ├── parsinlu_qa.yaml │ │ │ ├── parsinlu_reading_comprehension.yaml │ │ │ ├── penguins_in_a_table.yaml │ │ │ ├── periodic_elements.yaml │ │ │ ├── persian_idioms.yaml │ │ │ ├── phrase_relatedness.yaml │ │ │ ├── physical_intuition.yaml │ │ │ ├── physics.yaml │ │ │ ├── physics_questions.yaml │ │ │ ├── play_dialog_same_or_different.yaml │ │ │ ├── polish_sequence_labeling.yaml │ │ │ ├── presuppositions_as_nli.yaml │ │ │ ├── qa_wikidata.yaml │ │ │ ├── question_selection.yaml │ │ │ ├── real_or_fake_text.yaml │ │ │ ├── reasoning_about_colored_objects.yaml │ │ │ ├── repeat_copy_logic.yaml │ │ │ ├── rephrase.yaml │ │ │ ├── riddle_sense.yaml │ │ │ ├── ruin_names.yaml │ │ │ ├── salient_translation_error_detection.yaml │ │ │ ├── scientific_press_release.yaml │ │ │ ├── semantic_parsing_in_context_sparc.yaml │ │ │ ├── semantic_parsing_spider.yaml │ │ │ ├── sentence_ambiguity.yaml │ │ │ ├── similarities_abstraction.yaml │ │ │ ├── simp_turing_concept.yaml │ │ │ ├── simple_arithmetic_json.yaml │ │ │ ├── simple_arithmetic_json_multiple_choice.yaml │ │ │ ├── simple_arithmetic_json_subtasks.yaml │ │ │ ├── simple_arithmetic_multiple_targets_json.yaml │ │ │ ├── simple_ethical_questions.yaml │ │ │ ├── simple_text_editing.yaml │ │ │ ├── snarks.yaml │ │ │ ├── social_iqa.yaml │ │ │ ├── social_support.yaml │ │ │ ├── sports_understanding.yaml │ │ │ ├── strange_stories.yaml │ │ │ ├── strategyqa.yaml │ │ │ ├── sufficient_information.yaml │ │ │ ├── suicide_risk.yaml │ │ │ ├── swahili_english_proverbs.yaml │ │ │ ├── swedish_to_german_proverbs.yaml │ │ │ ├── symbol_interpretation.yaml │ │ │ ├── temporal_sequences.yaml │ │ │ ├── tense.yaml │ │ │ ├── timedial.yaml │ │ │ ├── topical_chat.yaml │ │ │ ├── tracking_shuffled_objects.yaml │ │ │ ├── understanding_fables.yaml │ │ │ ├── undo_permutation.yaml │ │ │ ├── unit_conversion.yaml │ │ │ ├── unit_interpretation.yaml │ │ │ ├── unnatural_in_context_learning.yaml │ │ │ ├── vitaminc_fact_verification.yaml │ │ │ ├── what_is_the_tao.yaml │ │ │ ├── which_wiki_edit.yaml │ │ │ ├── winowhy.yaml │ │ │ ├── word_sorting.yaml │ │ │ └── word_unscrambling.yaml │ │ ├── multiple_choice_template_yaml │ │ └── push_bigbench_dataset.py │ ├── blimp │ │ ├── README.md │ │ ├── adjunct_island.yaml │ │ ├── anaphor_gender_agreement.yaml │ │ ├── anaphor_number_agreement.yaml │ │ ├── animate_subject_passive.yaml │ │ ├── animate_subject_trans.yaml │ │ ├── causative.yaml │ │ ├── complex_NP_island.yaml │ │ ├── coordinate_structure_constraint_complex_left_branch.yaml │ │ ├── coordinate_structure_constraint_object_extraction.yaml │ │ ├── determiner_noun_agreement_1.yaml │ │ ├── determiner_noun_agreement_2.yaml │ │ ├── determiner_noun_agreement_irregular_1.yaml │ │ ├── determiner_noun_agreement_irregular_2.yaml │ │ ├── determiner_noun_agreement_with_adj_2.yaml │ │ ├── determiner_noun_agreement_with_adj_irregular_1.yaml │ │ ├── determiner_noun_agreement_with_adj_irregular_2.yaml │ │ ├── determiner_noun_agreement_with_adjective_1.yaml │ │ ├── distractor_agreement_relational_noun.yaml │ │ ├── distractor_agreement_relative_clause.yaml │ │ ├── drop_argument.yaml │ │ ├── ellipsis_n_bar_1.yaml │ │ ├── ellipsis_n_bar_2.yaml │ │ ├── existential_there_object_raising.yaml │ │ ├── existential_there_quantifiers_1.yaml │ │ ├── existential_there_quantifiers_2.yaml │ │ ├── existential_there_subject_raising.yaml │ │ ├── expletive_it_object_raising.yaml │ │ ├── generate_configs.py │ │ ├── inchoative.yaml │ │ ├── intransitive.yaml │ │ ├── irregular_past_participle_adjectives.yaml │ │ ├── irregular_past_participle_verbs.yaml │ │ ├── irregular_plural_subject_verb_agreement_1.yaml │ │ ├── irregular_plural_subject_verb_agreement_2.yaml │ │ ├── left_branch_island_echo_question.yaml │ │ ├── left_branch_island_simple_question.yaml │ │ ├── matrix_question_npi_licensor_present.yaml │ │ ├── npi_present_1.yaml │ │ ├── npi_present_2.yaml │ │ ├── only_npi_licensor_present.yaml │ │ ├── only_npi_scope.yaml │ │ ├── passive_1.yaml │ │ ├── passive_2.yaml │ │ ├── principle_A_c_command.yaml │ │ ├── principle_A_case_1.yaml │ │ ├── principle_A_case_2.yaml │ │ ├── principle_A_domain_1.yaml │ │ ├── principle_A_domain_2.yaml │ │ ├── principle_A_domain_3.yaml │ │ ├── principle_A_reconstruction.yaml │ │ ├── regular_plural_subject_verb_agreement_1.yaml │ │ ├── regular_plural_subject_verb_agreement_2.yaml │ │ ├── sentential_negation_npi_licensor_present.yaml │ │ ├── sentential_negation_npi_scope.yaml │ │ ├── sentential_subject_island.yaml │ │ ├── superlative_quantifiers_1.yaml │ │ ├── superlative_quantifiers_2.yaml │ │ ├── template_yaml │ │ ├── tough_vs_raising_1.yaml │ │ ├── tough_vs_raising_2.yaml │ │ ├── transitive.yaml │ │ ├── wh_island.yaml │ │ ├── wh_questions_object_gap.yaml │ │ ├── wh_questions_subject_gap.yaml │ │ ├── wh_questions_subject_gap_long_distance.yaml │ │ ├── wh_vs_that_no_gap.yaml │ │ ├── wh_vs_that_no_gap_long_distance.yaml │ │ ├── wh_vs_that_with_gap.yaml │ │ └── wh_vs_that_with_gap_long_distance.yaml │ ├── ceval │ │ ├── README.md │ │ ├── _default_ceval_yaml │ │ ├── _generate_configs.py │ │ ├── ceval-valid_accountant.yaml │ │ ├── ceval-valid_advanced_mathematics.yaml │ │ ├── ceval-valid_art_studies.yaml │ │ ├── ceval-valid_basic_medicine.yaml │ │ ├── ceval-valid_business_administration.yaml │ │ ├── ceval-valid_chinese_language_and_literature.yaml │ │ ├── ceval-valid_civil_servant.yaml │ │ ├── ceval-valid_clinical_medicine.yaml │ │ ├── ceval-valid_college_chemistry.yaml │ │ ├── ceval-valid_college_economics.yaml │ │ ├── ceval-valid_college_physics.yaml │ │ ├── ceval-valid_college_programming.yaml │ │ ├── ceval-valid_computer_architecture.yaml │ │ ├── ceval-valid_computer_network.yaml │ │ ├── ceval-valid_discrete_mathematics.yaml │ │ ├── ceval-valid_education_science.yaml │ │ ├── ceval-valid_electrical_engineer.yaml │ │ ├── ceval-valid_environmental_impact_assessment_engineer.yaml │ │ ├── ceval-valid_fire_engineer.yaml │ │ ├── ceval-valid_high_school_biology.yaml │ │ ├── ceval-valid_high_school_chemistry.yaml │ │ ├── ceval-valid_high_school_chinese.yaml │ │ ├── ceval-valid_high_school_geography.yaml │ │ ├── ceval-valid_high_school_history.yaml │ │ ├── ceval-valid_high_school_mathematics.yaml │ │ ├── ceval-valid_high_school_physics.yaml │ │ ├── ceval-valid_high_school_politics.yaml │ │ ├── ceval-valid_ideological_and_moral_cultivation.yaml │ │ ├── ceval-valid_law.yaml │ │ ├── ceval-valid_legal_professional.yaml │ │ ├── ceval-valid_logic.yaml │ │ ├── ceval-valid_mao_zedong_thought.yaml │ │ ├── ceval-valid_marxism.yaml │ │ ├── ceval-valid_metrology_engineer.yaml │ │ ├── ceval-valid_middle_school_biology.yaml │ │ ├── ceval-valid_middle_school_chemistry.yaml │ │ ├── ceval-valid_middle_school_geography.yaml │ │ ├── ceval-valid_middle_school_history.yaml │ │ ├── ceval-valid_middle_school_mathematics.yaml │ │ ├── ceval-valid_middle_school_physics.yaml │ │ ├── ceval-valid_middle_school_politics.yaml │ │ ├── ceval-valid_modern_chinese_history.yaml │ │ ├── ceval-valid_operating_system.yaml │ │ ├── ceval-valid_physician.yaml │ │ ├── ceval-valid_plant_protection.yaml │ │ ├── ceval-valid_probability_and_statistics.yaml │ │ ├── ceval-valid_professional_tour_guide.yaml │ │ ├── ceval-valid_sports_science.yaml │ │ ├── ceval-valid_tax_accountant.yaml │ │ ├── ceval-valid_teacher_qualification.yaml │ │ ├── ceval-valid_urban_and_rural_planner.yaml │ │ └── ceval-valid_veterinary_medicine.yaml │ ├── cmmlu │ │ ├── README.md │ │ ├── _default_template_yaml │ │ ├── _generate_configs.py │ │ ├── cmmlu_default_agronomy.yaml │ │ ├── cmmlu_default_anatomy.yaml │ │ ├── cmmlu_default_ancient_chinese.yaml │ │ ├── cmmlu_default_arts.yaml │ │ ├── cmmlu_default_astronomy.yaml │ │ ├── cmmlu_default_business_ethics.yaml │ │ ├── cmmlu_default_chinese_civil_service_exam.yaml │ │ ├── cmmlu_default_chinese_driving_rule.yaml │ │ ├── cmmlu_default_chinese_food_culture.yaml │ │ ├── cmmlu_default_chinese_foreign_policy.yaml │ │ ├── cmmlu_default_chinese_history.yaml │ │ ├── cmmlu_default_chinese_literature.yaml │ │ ├── cmmlu_default_chinese_teacher_qualification.yaml │ │ ├── cmmlu_default_clinical_knowledge.yaml │ │ ├── cmmlu_default_college_actuarial_science.yaml │ │ ├── cmmlu_default_college_education.yaml │ │ ├── cmmlu_default_college_engineering_hydrology.yaml │ │ ├── cmmlu_default_college_law.yaml │ │ ├── cmmlu_default_college_mathematics.yaml │ │ ├── cmmlu_default_college_medical_statistics.yaml │ │ ├── cmmlu_default_college_medicine.yaml │ │ ├── cmmlu_default_computer_science.yaml │ │ ├── cmmlu_default_computer_security.yaml │ │ ├── cmmlu_default_conceptual_physics.yaml │ │ ├── cmmlu_default_construction_project_management.yaml │ │ ├── cmmlu_default_economics.yaml │ │ ├── cmmlu_default_education.yaml │ │ ├── cmmlu_default_electrical_engineering.yaml │ │ ├── cmmlu_default_elementary_chinese.yaml │ │ ├── cmmlu_default_elementary_commonsense.yaml │ │ ├── cmmlu_default_elementary_information_and_technology.yaml │ │ ├── cmmlu_default_elementary_mathematics.yaml │ │ ├── cmmlu_default_ethnology.yaml │ │ ├── cmmlu_default_food_science.yaml │ │ ├── cmmlu_default_genetics.yaml │ │ ├── cmmlu_default_global_facts.yaml │ │ ├── cmmlu_default_high_school_biology.yaml │ │ ├── cmmlu_default_high_school_chemistry.yaml │ │ ├── cmmlu_default_high_school_geography.yaml │ │ ├── cmmlu_default_high_school_mathematics.yaml │ │ ├── cmmlu_default_high_school_physics.yaml │ │ ├── cmmlu_default_high_school_politics.yaml │ │ ├── cmmlu_default_human_sexuality.yaml │ │ ├── cmmlu_default_international_law.yaml │ │ ├── cmmlu_default_journalism.yaml │ │ ├── cmmlu_default_jurisprudence.yaml │ │ ├── cmmlu_default_legal_and_moral_basis.yaml │ │ ├── cmmlu_default_logical.yaml │ │ ├── cmmlu_default_machine_learning.yaml │ │ ├── cmmlu_default_management.yaml │ │ ├── cmmlu_default_marketing.yaml │ │ ├── cmmlu_default_marxist_theory.yaml │ │ ├── cmmlu_default_modern_chinese.yaml │ │ ├── cmmlu_default_nutrition.yaml │ │ ├── cmmlu_default_philosophy.yaml │ │ ├── cmmlu_default_professional_accounting.yaml │ │ ├── cmmlu_default_professional_law.yaml │ │ ├── cmmlu_default_professional_medicine.yaml │ │ ├── cmmlu_default_professional_psychology.yaml │ │ ├── cmmlu_default_public_relations.yaml │ │ ├── cmmlu_default_security_study.yaml │ │ ├── cmmlu_default_sociology.yaml │ │ ├── cmmlu_default_sports_science.yaml │ │ ├── cmmlu_default_traditional_chinese_medicine.yaml │ │ ├── cmmlu_default_virology.yaml │ │ ├── cmmlu_default_world_history.yaml │ │ └── cmmlu_default_world_religions.yaml │ ├── code_x_glue │ │ └── code-text │ │ │ ├── bleu.py │ │ │ ├── go.yaml │ │ │ ├── java.yaml │ │ │ ├── javascript.yaml │ │ │ ├── php.yaml │ │ │ ├── python.yaml │ │ │ ├── ruby.yaml │ │ │ └── utils.py │ ├── coqa │ │ ├── README.md │ │ ├── default.yaml │ │ └── utils.py │ ├── crows_pairs │ │ ├── README.md │ │ ├── crows_pairs_english.yaml │ │ ├── crows_pairs_english_age.yaml │ │ ├── crows_pairs_english_autre.yaml │ │ ├── crows_pairs_english_disability.yaml │ │ ├── crows_pairs_english_gender.yaml │ │ ├── crows_pairs_english_nationality.yaml │ │ ├── crows_pairs_english_physical_appearance.yaml │ │ ├── crows_pairs_english_race_color.yaml │ │ ├── crows_pairs_english_religion.yaml │ │ ├── crows_pairs_english_sexual_orientation.yaml │ │ ├── crows_pairs_english_socioeconomic.yaml │ │ ├── crows_pairs_french.yaml │ │ ├── crows_pairs_french_age.yaml │ │ ├── crows_pairs_french_autre.yaml │ │ ├── crows_pairs_french_disability.yaml │ │ ├── crows_pairs_french_gender.yaml │ │ ├── crows_pairs_french_nationality.yaml │ │ ├── crows_pairs_french_physical_appearance.yaml │ │ ├── crows_pairs_french_race_color.yaml │ │ ├── crows_pairs_french_religion.yaml │ │ ├── crows_pairs_french_sexual_orientation.yaml │ │ ├── crows_pairs_french_socioeconomic.yaml │ │ └── utils.py │ ├── csatqa │ │ ├── _default_csatqa_yaml │ │ ├── _generate_configs.py │ │ ├── csatqa_gr.yaml │ │ ├── csatqa_li.yaml │ │ ├── csatqa_rch.yaml │ │ ├── csatqa_rcs.yaml │ │ ├── csatqa_rcss.yaml │ │ ├── csatqa_wr.yaml │ │ └── utils.py │ ├── drop │ │ ├── README.md │ │ ├── default.yaml │ │ └── utils.py │ ├── glue │ │ ├── README.md │ │ ├── cola │ │ │ └── default.yaml │ │ ├── mnli │ │ │ ├── default.yaml │ │ │ ├── mismatch.yaml │ │ │ └── utils.py │ │ ├── mrpc │ │ │ └── default.yaml │ │ ├── qnli │ │ │ └── default.yaml │ │ ├── qqp │ │ │ └── default.yaml │ │ ├── rte │ │ │ └── default.yaml │ │ ├── sst │ │ │ └── default.yaml │ │ └── wnli │ │ │ └── default.yaml │ ├── gsm8k │ │ ├── README.md │ │ ├── gsm8k-cot-self-consistency.yaml │ │ ├── gsm8k-cot.yaml │ │ └── gsm8k.yaml │ ├── headqa │ │ ├── README.md │ │ ├── headqa_en.yaml │ │ └── headqa_es.yaml │ ├── hellaswag │ │ ├── README.md │ │ ├── hellaswag.yaml │ │ └── utils.py │ ├── hendrycks_ethics │ │ ├── README.md │ │ ├── commonsense.yaml │ │ ├── deontology.yaml │ │ ├── justice.yaml │ │ ├── utilitarianism.yaml │ │ ├── utilitarianism_original_yaml │ │ ├── utils.py │ │ └── virtue.yaml │ ├── lambada │ │ ├── README.md │ │ ├── lambada_openai.yaml │ │ └── lambada_standard.yaml │ ├── lambada_cloze │ │ ├── README.md │ │ ├── lambada_openai_cloze.yaml │ │ └── lambada_standard_cloze.yaml │ ├── lambada_multilingual │ │ ├── README.md │ │ ├── lambada_mt_de.yaml │ │ ├── lambada_mt_en.yaml │ │ ├── lambada_mt_es.yaml │ │ ├── lambada_mt_fr.yaml │ │ └── lambada_mt_it.yaml │ ├── logiqa │ │ ├── README.md │ │ ├── logiqa.yaml │ │ └── utils_logiqa.py │ ├── logiqa2 │ │ ├── README.md │ │ ├── logieval.yaml │ │ ├── logiqa2.yaml │ │ └── utils_logiqa2.py │ ├── mathqa │ │ ├── README.md │ │ ├── mathqa.yaml │ │ └── utils.py │ ├── mc_taco │ │ ├── README.md │ │ └── default.yaml │ ├── mgsm │ │ ├── README.md │ │ ├── direct │ │ │ ├── direct_yaml │ │ │ ├── mgsm_direct_bn.yaml │ │ │ ├── mgsm_direct_de.yaml │ │ │ ├── mgsm_direct_en.yaml │ │ │ ├── mgsm_direct_es.yaml │ │ │ ├── mgsm_direct_fr.yaml │ │ │ ├── mgsm_direct_ja.yaml │ │ │ ├── mgsm_direct_ru.yaml │ │ │ ├── mgsm_direct_sw.yaml │ │ │ ├── mgsm_direct_te.yaml │ │ │ ├── mgsm_direct_th.yaml │ │ │ └── mgsm_direct_zh.yaml │ │ ├── en_cot │ │ │ ├── cot_yaml │ │ │ ├── mgsm_bn_en-cot.yaml │ │ │ ├── mgsm_de_en-cot.yaml │ │ │ ├── mgsm_en_en-cot.yaml │ │ │ ├── mgsm_es_en-cot.yaml │ │ │ ├── mgsm_fr_en-cot.yaml │ │ │ ├── mgsm_ja_en-cot.yaml │ │ │ ├── mgsm_ru_en-cot.yaml │ │ │ ├── mgsm_sw_en-cot.yaml │ │ │ ├── mgsm_te_en-cot.yaml │ │ │ ├── mgsm_th_en-cot.yaml │ │ │ └── mgsm_zh_en-cot.yaml │ │ ├── native_cot │ │ │ ├── cot_yaml │ │ │ ├── mgsm_cot_native_bn.yaml │ │ │ ├── mgsm_cot_native_de.yaml │ │ │ ├── mgsm_cot_native_en.yaml │ │ │ ├── mgsm_cot_native_es.yaml │ │ │ ├── mgsm_cot_native_fr.yaml │ │ │ ├── mgsm_cot_native_ja.yaml │ │ │ ├── mgsm_cot_native_ru.yaml │ │ │ ├── mgsm_cot_native_sw.yaml │ │ │ ├── mgsm_cot_native_te.yaml │ │ │ ├── mgsm_cot_native_th.yaml │ │ │ └── mgsm_cot_native_zh.yaml │ │ └── utils.py │ ├── minerva_math │ │ ├── README.md │ │ ├── minerva_math_algebra.yaml │ │ ├── minerva_math_counting_and_prob.yaml │ │ ├── minerva_math_geometry.yaml │ │ ├── minerva_math_intermediate_algebra.yaml │ │ ├── minerva_math_num_theory.yaml │ │ ├── minerva_math_prealgebra.yaml │ │ ├── minerva_math_precalc.yaml │ │ └── utils.py │ ├── mmlu │ │ ├── _cot_prompts.json │ │ ├── _generate_configs.py │ │ ├── default │ │ │ ├── _default_template_yaml │ │ │ ├── mmlu_abstract_algebra.yaml │ │ │ ├── mmlu_anatomy.yaml │ │ │ ├── mmlu_astronomy.yaml │ │ │ ├── mmlu_business_ethics.yaml │ │ │ ├── mmlu_clinical_knowledge.yaml │ │ │ ├── mmlu_college_biology.yaml │ │ │ ├── mmlu_college_chemistry.yaml │ │ │ ├── mmlu_college_computer_science.yaml │ │ │ ├── mmlu_college_mathematics.yaml │ │ │ ├── mmlu_college_medicine.yaml │ │ │ ├── mmlu_college_physics.yaml │ │ │ ├── mmlu_computer_security.yaml │ │ │ ├── mmlu_conceptual_physics.yaml │ │ │ ├── mmlu_econometrics.yaml │ │ │ ├── mmlu_electrical_engineering.yaml │ │ │ ├── mmlu_elementary_mathematics.yaml │ │ │ ├── mmlu_formal_logic.yaml │ │ │ ├── mmlu_global_facts.yaml │ │ │ ├── mmlu_high_school_biology.yaml │ │ │ ├── mmlu_high_school_chemistry.yaml │ │ │ ├── mmlu_high_school_computer_science.yaml │ │ │ ├── mmlu_high_school_european_history.yaml │ │ │ ├── mmlu_high_school_geography.yaml │ │ │ ├── mmlu_high_school_government_and_politics.yaml │ │ │ ├── mmlu_high_school_macroeconomics.yaml │ │ │ ├── mmlu_high_school_mathematics.yaml │ │ │ ├── mmlu_high_school_microeconomics.yaml │ │ │ ├── mmlu_high_school_physics.yaml │ │ │ ├── mmlu_high_school_psychology.yaml │ │ │ ├── mmlu_high_school_statistics.yaml │ │ │ ├── mmlu_high_school_us_history.yaml │ │ │ ├── mmlu_high_school_world_history.yaml │ │ │ ├── mmlu_human_aging.yaml │ │ │ ├── mmlu_human_sexuality.yaml │ │ │ ├── mmlu_international_law.yaml │ │ │ ├── mmlu_jurisprudence.yaml │ │ │ ├── mmlu_logical_fallacies.yaml │ │ │ ├── mmlu_machine_learning.yaml │ │ │ ├── mmlu_management.yaml │ │ │ ├── mmlu_marketing.yaml │ │ │ ├── mmlu_medical_genetics.yaml │ │ │ ├── mmlu_miscellaneous.yaml │ │ │ ├── mmlu_moral_disputes.yaml │ │ │ ├── mmlu_moral_scenarios.yaml │ │ │ ├── mmlu_nutrition.yaml │ │ │ ├── mmlu_philosophy.yaml │ │ │ ├── mmlu_prehistory.yaml │ │ │ ├── mmlu_professional_accounting.yaml │ │ │ ├── mmlu_professional_law.yaml │ │ │ ├── mmlu_professional_medicine.yaml │ │ │ ├── mmlu_professional_psychology.yaml │ │ │ ├── mmlu_public_relations.yaml │ │ │ ├── mmlu_security_studies.yaml │ │ │ ├── mmlu_sociology.yaml │ │ │ ├── mmlu_us_foreign_policy.yaml │ │ │ ├── mmlu_virology.yaml │ │ │ └── mmlu_world_religions.yaml │ │ ├── flan_cot_fewshot │ │ │ ├── _mmlu_flan_cot_fewshot_template_yaml │ │ │ ├── mmlu_abstract_algebra.yaml │ │ │ ├── mmlu_anatomy.yaml │ │ │ ├── mmlu_astronomy.yaml │ │ │ ├── mmlu_business_ethics.yaml │ │ │ ├── mmlu_clinical_knowledge.yaml │ │ │ ├── mmlu_college_biology.yaml │ │ │ ├── mmlu_college_chemistry.yaml │ │ │ ├── mmlu_college_computer_science.yaml │ │ │ ├── mmlu_college_mathematics.yaml │ │ │ ├── mmlu_college_medicine.yaml │ │ │ ├── mmlu_college_physics.yaml │ │ │ ├── mmlu_computer_security.yaml │ │ │ ├── mmlu_conceptual_physics.yaml │ │ │ ├── mmlu_econometrics.yaml │ │ │ ├── mmlu_electrical_engineering.yaml │ │ │ ├── mmlu_elementary_mathematics.yaml │ │ │ ├── mmlu_formal_logic.yaml │ │ │ ├── mmlu_global_facts.yaml │ │ │ ├── mmlu_high_school_biology.yaml │ │ │ ├── mmlu_high_school_chemistry.yaml │ │ │ ├── mmlu_high_school_computer_science.yaml │ │ │ ├── mmlu_high_school_european_history.yaml │ │ │ ├── mmlu_high_school_geography.yaml │ │ │ ├── mmlu_high_school_government_and_politics.yaml │ │ │ ├── mmlu_high_school_macroeconomics.yaml │ │ │ ├── mmlu_high_school_mathematics.yaml │ │ │ ├── mmlu_high_school_microeconomics.yaml │ │ │ ├── mmlu_high_school_physics.yaml │ │ │ ├── mmlu_high_school_psychology.yaml │ │ │ ├── mmlu_high_school_statistics.yaml │ │ │ ├── mmlu_high_school_us_history.yaml │ │ │ ├── mmlu_high_school_world_history.yaml │ │ │ ├── mmlu_human_aging.yaml │ │ │ ├── mmlu_human_sexuality.yaml │ │ │ ├── mmlu_international_law.yaml │ │ │ ├── mmlu_jurisprudence.yaml │ │ │ ├── mmlu_logical_fallacies.yaml │ │ │ ├── mmlu_machine_learning.yaml │ │ │ ├── mmlu_management.yaml │ │ │ ├── mmlu_marketing.yaml │ │ │ ├── mmlu_medical_genetics.yaml │ │ │ ├── mmlu_miscellaneous.yaml │ │ │ ├── mmlu_moral_disputes.yaml │ │ │ ├── mmlu_moral_scenarios.yaml │ │ │ ├── mmlu_nutrition.yaml │ │ │ ├── mmlu_philosophy.yaml │ │ │ ├── mmlu_prehistory.yaml │ │ │ ├── mmlu_professional_accounting.yaml │ │ │ ├── mmlu_professional_law.yaml │ │ │ ├── mmlu_professional_medicine.yaml │ │ │ ├── mmlu_professional_psychology.yaml │ │ │ ├── mmlu_public_relations.yaml │ │ │ ├── mmlu_security_studies.yaml │ │ │ ├── mmlu_sociology.yaml │ │ │ ├── mmlu_us_foreign_policy.yaml │ │ │ ├── mmlu_virology.yaml │ │ │ └── mmlu_world_religions.yaml │ │ ├── flan_cot_zeroshot │ │ │ ├── _mmlu_flan_generative_template_yaml │ │ │ ├── mmlu_abstract_algebra.yaml │ │ │ ├── mmlu_anatomy.yaml │ │ │ ├── mmlu_astronomy.yaml │ │ │ ├── mmlu_business_ethics.yaml │ │ │ ├── mmlu_clinical_knowledge.yaml │ │ │ ├── mmlu_college_biology.yaml │ │ │ ├── mmlu_college_chemistry.yaml │ │ │ ├── mmlu_college_computer_science.yaml │ │ │ ├── mmlu_college_mathematics.yaml │ │ │ ├── mmlu_college_medicine.yaml │ │ │ ├── mmlu_college_physics.yaml │ │ │ ├── mmlu_computer_security.yaml │ │ │ ├── mmlu_conceptual_physics.yaml │ │ │ ├── mmlu_econometrics.yaml │ │ │ ├── mmlu_electrical_engineering.yaml │ │ │ ├── mmlu_elementary_mathematics.yaml │ │ │ ├── mmlu_formal_logic.yaml │ │ │ ├── mmlu_global_facts.yaml │ │ │ ├── mmlu_high_school_biology.yaml │ │ │ ├── mmlu_high_school_chemistry.yaml │ │ │ ├── mmlu_high_school_computer_science.yaml │ │ │ ├── mmlu_high_school_european_history.yaml │ │ │ ├── mmlu_high_school_geography.yaml │ │ │ ├── mmlu_high_school_government_and_politics.yaml │ │ │ ├── mmlu_high_school_macroeconomics.yaml │ │ │ ├── mmlu_high_school_mathematics.yaml │ │ │ ├── mmlu_high_school_microeconomics.yaml │ │ │ ├── mmlu_high_school_physics.yaml │ │ │ ├── mmlu_high_school_psychology.yaml │ │ │ ├── mmlu_high_school_statistics.yaml │ │ │ ├── mmlu_high_school_us_history.yaml │ │ │ ├── mmlu_high_school_world_history.yaml │ │ │ ├── mmlu_human_aging.yaml │ │ │ ├── mmlu_human_sexuality.yaml │ │ │ ├── mmlu_international_law.yaml │ │ │ ├── mmlu_jurisprudence.yaml │ │ │ ├── mmlu_logical_fallacies.yaml │ │ │ ├── mmlu_machine_learning.yaml │ │ │ ├── mmlu_management.yaml │ │ │ ├── mmlu_marketing.yaml │ │ │ ├── mmlu_medical_genetics.yaml │ │ │ ├── mmlu_miscellaneous.yaml │ │ │ ├── mmlu_moral_disputes.yaml │ │ │ ├── mmlu_moral_scenarios.yaml │ │ │ ├── mmlu_nutrition.yaml │ │ │ ├── mmlu_philosophy.yaml │ │ │ ├── mmlu_prehistory.yaml │ │ │ ├── mmlu_professional_accounting.yaml │ │ │ ├── mmlu_professional_law.yaml │ │ │ ├── mmlu_professional_medicine.yaml │ │ │ ├── mmlu_professional_psychology.yaml │ │ │ ├── mmlu_public_relations.yaml │ │ │ ├── mmlu_security_studies.yaml │ │ │ ├── mmlu_sociology.yaml │ │ │ ├── mmlu_us_foreign_policy.yaml │ │ │ ├── mmlu_virology.yaml │ │ │ └── mmlu_world_religions.yaml │ │ └── flan_n_shot │ │ │ ├── _mmlu_flan_generative_template_yaml │ │ │ ├── _mmlu_flan_loglikelihood_template_yaml │ │ │ ├── mmlu_gen_abstract_algebra.yaml │ │ │ ├── mmlu_gen_anatomy.yaml │ │ │ ├── mmlu_gen_astronomy.yaml │ │ │ ├── mmlu_gen_business_ethics.yaml │ │ │ ├── mmlu_gen_clinical_knowledge.yaml │ │ │ ├── mmlu_gen_college_biology.yaml │ │ │ ├── mmlu_gen_college_chemistry.yaml │ │ │ ├── mmlu_gen_college_computer_science.yaml │ │ │ ├── mmlu_gen_college_mathematics.yaml │ │ │ ├── mmlu_gen_college_medicine.yaml │ │ │ ├── mmlu_gen_college_physics.yaml │ │ │ ├── mmlu_gen_computer_security.yaml │ │ │ ├── mmlu_gen_conceptual_physics.yaml │ │ │ ├── mmlu_gen_econometrics.yaml │ │ │ ├── mmlu_gen_electrical_engineering.yaml │ │ │ ├── mmlu_gen_elementary_mathematics.yaml │ │ │ ├── mmlu_gen_formal_logic.yaml │ │ │ ├── mmlu_gen_global_facts.yaml │ │ │ ├── mmlu_gen_high_school_biology.yaml │ │ │ ├── mmlu_gen_high_school_chemistry.yaml │ │ │ ├── mmlu_gen_high_school_computer_science.yaml │ │ │ ├── mmlu_gen_high_school_european_history.yaml │ │ │ ├── mmlu_gen_high_school_geography.yaml │ │ │ ├── mmlu_gen_high_school_government_and_politics.yaml │ │ │ ├── mmlu_gen_high_school_macroeconomics.yaml │ │ │ ├── mmlu_gen_high_school_mathematics.yaml │ │ │ ├── mmlu_gen_high_school_microeconomics.yaml │ │ │ ├── mmlu_gen_high_school_physics.yaml │ │ │ ├── mmlu_gen_high_school_psychology.yaml │ │ │ ├── mmlu_gen_high_school_statistics.yaml │ │ │ ├── mmlu_gen_high_school_us_history.yaml │ │ │ ├── mmlu_gen_high_school_world_history.yaml │ │ │ ├── mmlu_gen_human_aging.yaml │ │ │ ├── mmlu_gen_human_sexuality.yaml │ │ │ ├── mmlu_gen_international_law.yaml │ │ │ ├── mmlu_gen_jurisprudence.yaml │ │ │ ├── mmlu_gen_logical_fallacies.yaml │ │ │ ├── mmlu_gen_machine_learning.yaml │ │ │ ├── mmlu_gen_management.yaml │ │ │ ├── mmlu_gen_marketing.yaml │ │ │ ├── mmlu_gen_medical_genetics.yaml │ │ │ ├── mmlu_gen_miscellaneous.yaml │ │ │ ├── mmlu_gen_moral_disputes.yaml │ │ │ ├── mmlu_gen_moral_scenarios.yaml │ │ │ ├── mmlu_gen_nutrition.yaml │ │ │ ├── mmlu_gen_philosophy.yaml │ │ │ ├── mmlu_gen_prehistory.yaml │ │ │ ├── mmlu_gen_professional_accounting.yaml │ │ │ ├── mmlu_gen_professional_law.yaml │ │ │ ├── mmlu_gen_professional_medicine.yaml │ │ │ ├── mmlu_gen_professional_psychology.yaml │ │ │ ├── mmlu_gen_public_relations.yaml │ │ │ ├── mmlu_gen_security_studies.yaml │ │ │ ├── mmlu_gen_sociology.yaml │ │ │ ├── mmlu_gen_us_foreign_policy.yaml │ │ │ ├── mmlu_gen_virology.yaml │ │ │ ├── mmlu_gen_world_religions.yaml │ │ │ ├── mmlu_log_abstract_algebra.yaml │ │ │ ├── mmlu_log_anatomy.yaml │ │ │ ├── mmlu_log_astronomy.yaml │ │ │ ├── mmlu_log_business_ethics.yaml │ │ │ ├── mmlu_log_clinical_knowledge.yaml │ │ │ ├── mmlu_log_college_biology.yaml │ │ │ ├── mmlu_log_college_chemistry.yaml │ │ │ ├── mmlu_log_college_computer_science.yaml │ │ │ ├── mmlu_log_college_mathematics.yaml │ │ │ ├── mmlu_log_college_medicine.yaml │ │ │ ├── mmlu_log_college_physics.yaml │ │ │ ├── mmlu_log_computer_security.yaml │ │ │ ├── mmlu_log_conceptual_physics.yaml │ │ │ ├── mmlu_log_econometrics.yaml │ │ │ ├── mmlu_log_electrical_engineering.yaml │ │ │ ├── mmlu_log_elementary_mathematics.yaml │ │ │ ├── mmlu_log_formal_logic.yaml │ │ │ ├── mmlu_log_global_facts.yaml │ │ │ ├── mmlu_log_high_school_biology.yaml │ │ │ ├── mmlu_log_high_school_chemistry.yaml │ │ │ ├── mmlu_log_high_school_computer_science.yaml │ │ │ ├── mmlu_log_high_school_european_history.yaml │ │ │ ├── mmlu_log_high_school_geography.yaml │ │ │ ├── mmlu_log_high_school_government_and_politics.yaml │ │ │ ├── mmlu_log_high_school_macroeconomics.yaml │ │ │ ├── mmlu_log_high_school_mathematics.yaml │ │ │ ├── mmlu_log_high_school_microeconomics.yaml │ │ │ ├── mmlu_log_high_school_physics.yaml │ │ │ ├── mmlu_log_high_school_psychology.yaml │ │ │ ├── mmlu_log_high_school_statistics.yaml │ │ │ ├── mmlu_log_high_school_us_history.yaml │ │ │ ├── mmlu_log_high_school_world_history.yaml │ │ │ ├── mmlu_log_human_aging.yaml │ │ │ ├── mmlu_log_human_sexuality.yaml │ │ │ ├── mmlu_log_international_law.yaml │ │ │ ├── mmlu_log_jurisprudence.yaml │ │ │ ├── mmlu_log_logical_fallacies.yaml │ │ │ ├── mmlu_log_machine_learning.yaml │ │ │ ├── mmlu_log_management.yaml │ │ │ ├── mmlu_log_marketing.yaml │ │ │ ├── mmlu_log_medical_genetics.yaml │ │ │ ├── mmlu_log_miscellaneous.yaml │ │ │ ├── mmlu_log_moral_disputes.yaml │ │ │ ├── mmlu_log_moral_scenarios.yaml │ │ │ ├── mmlu_log_nutrition.yaml │ │ │ ├── mmlu_log_philosophy.yaml │ │ │ ├── mmlu_log_prehistory.yaml │ │ │ ├── mmlu_log_professional_accounting.yaml │ │ │ ├── mmlu_log_professional_law.yaml │ │ │ ├── mmlu_log_professional_medicine.yaml │ │ │ ├── mmlu_log_professional_psychology.yaml │ │ │ ├── mmlu_log_public_relations.yaml │ │ │ ├── mmlu_log_security_studies.yaml │ │ │ ├── mmlu_log_sociology.yaml │ │ │ ├── mmlu_log_us_foreign_policy.yaml │ │ │ ├── mmlu_log_virology.yaml │ │ │ └── mmlu_log_world_religions.yaml │ ├── mutual │ │ ├── README.md │ │ ├── multual_plus.yaml │ │ ├── mutual.yaml │ │ └── utils.py │ ├── nq_open │ │ ├── README.md │ │ └── nq_open.yaml │ ├── openbookqa │ │ ├── README.md │ │ └── openbookqa.yaml │ ├── paws-x │ │ ├── README.md │ │ ├── _generate_config.py │ │ ├── paws_de.yaml │ │ ├── paws_en.yaml │ │ ├── paws_es.yaml │ │ ├── paws_fr.yaml │ │ ├── paws_ja.yaml │ │ ├── paws_ko.yaml │ │ ├── paws_zh.yaml │ │ └── pawsx_template_yaml │ ├── pile │ │ ├── README.md │ │ ├── pile_arxiv.yaml │ │ ├── pile_bookcorpus2.yaml │ │ ├── pile_books3.yaml │ │ ├── pile_dm-mathematics.yaml │ │ ├── pile_enron.yaml │ │ ├── pile_europarl.yaml │ │ ├── pile_freelaw.yaml │ │ ├── pile_github.yaml │ │ ├── pile_gutenberg.yaml │ │ ├── pile_hackernews.yaml │ │ ├── pile_nih-exporter.yaml │ │ ├── pile_opensubtitles.yaml │ │ ├── pile_openwebtext2.yaml │ │ ├── pile_philpapers.yaml │ │ ├── pile_pile-cc.yaml │ │ ├── pile_pubmed-abstracts.yaml │ │ ├── pile_pubmed-central.yaml │ │ ├── pile_stackexchange.yaml │ │ ├── pile_ubuntu-irc.yaml │ │ ├── pile_uspto.yaml │ │ ├── pile_wikipedia.yaml │ │ └── pile_youtubesubtitles.yaml │ ├── piqa │ │ ├── README.md │ │ └── piqa.yaml │ ├── polemo2 │ │ ├── README.md │ │ ├── polemo2_in.yaml │ │ └── polemo2_out.yaml │ ├── prost │ │ ├── README.md │ │ └── corypaik_prost.yaml │ ├── pubmedqa │ │ ├── README.md │ │ ├── preprocess_pubmedqa.py │ │ └── pubmedqa.yaml │ ├── qa4mre │ │ ├── README.md │ │ ├── preprocess_qa4mre.py │ │ ├── qa4mre_2011.yaml │ │ ├── qa4mre_2012.yaml │ │ └── qa4mre_2013.yaml │ ├── qasper │ │ ├── README.md │ │ ├── bool.yaml │ │ ├── freeform.yaml │ │ ├── metrics.py │ │ └── utils.py │ ├── race │ │ ├── README.md │ │ ├── preprocess_race.py │ │ └── race.yaml │ ├── realtoxicityprompts │ │ ├── metric.py │ │ └── realtoxicityprompts.yaml │ ├── sciq │ │ ├── README.md │ │ └── sciq.yaml │ ├── squadv2 │ │ ├── README.md │ │ ├── default.yaml │ │ ├── no_ans.yaml │ │ ├── utils.py │ │ └── with_noans_prob.yaml │ ├── storycloze │ │ ├── README.md │ │ ├── storycloze_2016.yaml │ │ └── storycloze_2018.yaml │ ├── super_glue │ │ ├── README.md │ │ ├── boolq │ │ │ ├── default.yaml │ │ │ ├── seq2seq.yaml │ │ │ └── t5-prompt.yaml │ │ ├── cb │ │ │ ├── aggregate.py │ │ │ ├── default.yaml │ │ │ ├── t5-prompt.yaml │ │ │ └── t5_utils.py │ │ ├── copa │ │ │ ├── default.yaml │ │ │ ├── t5-prompt.yaml │ │ │ └── utils.py │ │ ├── multirc │ │ │ ├── default.yaml │ │ │ ├── t5-prompt.yaml │ │ │ └── t5_utils.py │ │ ├── record │ │ │ ├── default.yaml │ │ │ ├── t5-prompt.yaml │ │ │ ├── t5_utils.py │ │ │ └── util.py │ │ ├── rte │ │ │ ├── default.yaml │ │ │ └── t5-prompt.yaml │ │ ├── wic │ │ │ ├── default.yaml │ │ │ └── t5-prompt.yaml │ │ └── wsc │ │ │ ├── default.yaml │ │ │ ├── preprocess_wsc.py │ │ │ ├── t5-prompt.yaml │ │ │ └── t5_utils.py │ ├── swag │ │ ├── README.md │ │ └── swag.yaml │ ├── toxigen │ │ ├── README.md │ │ ├── toxigen.yaml │ │ └── utils.py │ ├── translation │ │ ├── README.md │ │ ├── iwslt2017_ar-en.yaml │ │ ├── iwslt2017_en-ar.yaml │ │ ├── utils.py │ │ ├── wmt14_en-fr.yaml │ │ ├── wmt14_fr-en.yaml │ │ ├── wmt16_de-en.yaml │ │ ├── wmt16_en-de.yaml │ │ ├── wmt16_en-ro.yaml │ │ ├── wmt16_ro-en.yaml │ │ └── wmt_common_yaml │ ├── triviaqa │ │ ├── README.md │ │ └── default.yaml │ ├── truthfulqa │ │ ├── README.md │ │ ├── truthfulqa_gen.yaml │ │ ├── truthfulqa_mc1.yaml │ │ ├── truthfulqa_mc2.yaml │ │ └── utils.py │ ├── unscramble │ │ ├── README.md │ │ ├── anagrams1.yaml │ │ ├── anagrams2.yaml │ │ ├── cycle_letters.yaml │ │ ├── random_insertion.yaml │ │ └── reversed_words.yaml │ ├── webqs │ │ ├── README.md │ │ ├── utils.py │ │ └── webqs.yaml │ ├── wikitext │ │ ├── README.md │ │ ├── preprocess_wikitext.py │ │ └── wikitext.yaml │ ├── winogrande │ │ ├── README.md │ │ ├── default.yaml │ │ └── preprocess_winogrande.py │ ├── wmt2016 │ │ ├── README.md │ │ ├── metrics.py │ │ └── ro_en-t5_prompt.yaml │ ├── wsc273 │ │ ├── README.md │ │ ├── default.yaml │ │ └── utils.py │ ├── xcopa │ │ ├── README.md │ │ ├── default_et.yaml │ │ ├── default_ht.yaml │ │ ├── default_id.yaml │ │ ├── default_it.yaml │ │ ├── default_qu.yaml │ │ ├── default_sw.yaml │ │ ├── default_ta.yaml │ │ ├── default_th.yaml │ │ ├── default_tr.yaml │ │ ├── default_vi.yaml │ │ ├── default_zh.yaml │ │ └── utils.py │ ├── xnli │ │ ├── README.md │ │ ├── utils.py │ │ ├── xnli_ar.yaml │ │ ├── xnli_bg.yaml │ │ ├── xnli_common_yaml │ │ ├── xnli_de.yaml │ │ ├── xnli_el.yaml │ │ ├── xnli_en.yaml │ │ ├── xnli_es.yaml │ │ ├── xnli_fr.yaml │ │ ├── xnli_hi.yaml │ │ ├── xnli_ru.yaml │ │ ├── xnli_sw.yaml │ │ ├── xnli_th.yaml │ │ ├── xnli_tr.yaml │ │ ├── xnli_ur.yaml │ │ ├── xnli_vi.yaml │ │ └── xnli_zh.yaml │ ├── xstorycloze │ │ ├── README.md │ │ ├── default_ar.yaml │ │ ├── default_en.yaml │ │ ├── default_es.yaml │ │ ├── default_eu.yaml │ │ ├── default_hi.yaml │ │ ├── default_id.yaml │ │ ├── default_my.yaml │ │ ├── default_ru.yaml │ │ ├── default_sw.yaml │ │ ├── default_te.yaml │ │ └── default_zh.yaml │ └── xwinograd │ │ ├── README.md │ │ ├── utils.py │ │ ├── xwinograd_common_yaml │ │ ├── xwinograd_en.yaml │ │ ├── xwinograd_fr.yaml │ │ ├── xwinograd_jp.yaml │ │ ├── xwinograd_pt.yaml │ │ ├── xwinograd_ru.yaml │ │ └── xwinograd_zh.yaml └── utils.py ├── mypy.ini ├── pile_statistics.json ├── pyproject.toml ├── requirements.txt ├── scripts ├── __init__.py ├── build_benchmark.py ├── clean_training_data │ ├── README.md │ ├── __init__.py │ ├── compress_and_package.py │ ├── generate_13_grams.py │ ├── investigate_pile.py │ ├── janitor_util.cpp │ ├── process_sorted_buckets.py │ └── sort_13_gram_buckets.py ├── cost_estimate.py ├── get_prompts.py ├── make_gpt2_test_cases.py ├── make_table_results.py ├── make_table_tasks.py ├── regression.py └── write_out.py ├── setup.py ├── templates └── new_yaml_task │ ├── README.md │ └── blank_yaml.yaml └── tests ├── __init__.py ├── models └── test_huggingface.py ├── test_evaluator.py ├── test_janitor.py ├── test_misc.py ├── test_tasks.py ├── test_utils.py ├── testdata ├── anagrams1-v0-greedy_until ├── anagrams1-v0-res.json ├── anagrams2-v0-greedy_until ├── anagrams2-v0-res.json ├── anli_r1-v0-loglikelihood ├── anli_r1-v0-res.json ├── anli_r2-v0-loglikelihood ├── anli_r2-v0-res.json ├── anli_r3-v0-loglikelihood ├── anli_r3-v0-res.json ├── arc_challenge-v0-loglikelihood ├── arc_challenge-v0-res.json ├── arc_challenge-v2.0-loglikelihood ├── arc_challenge-v2.0-res.json ├── arc_easy-v0-loglikelihood ├── arc_easy-v0-res.json ├── arithmetic_1dc-v0-loglikelihood ├── arithmetic_1dc-v0-res.json ├── arithmetic_2da-v0-loglikelihood ├── arithmetic_2da-v0-res.json ├── arithmetic_2dm-v0-loglikelihood ├── arithmetic_2dm-v0-res.json ├── arithmetic_2ds-v0-loglikelihood ├── arithmetic_2ds-v0-res.json ├── arithmetic_3da-v0-loglikelihood ├── arithmetic_3da-v0-res.json ├── arithmetic_3ds-v0-loglikelihood ├── arithmetic_3ds-v0-res.json ├── arithmetic_4da-v0-loglikelihood ├── arithmetic_4da-v0-res.json ├── arithmetic_4ds-v0-loglikelihood ├── arithmetic_4ds-v0-res.json ├── arithmetic_5da-v0-loglikelihood ├── arithmetic_5da-v0-res.json ├── arithmetic_5ds-v0-loglikelihood ├── arithmetic_5ds-v0-res.json ├── blimp_adjunct_island-v0-loglikelihood ├── blimp_adjunct_island-v0-res.json ├── blimp_anaphor_gender_agreement-v0-loglikelihood ├── blimp_anaphor_gender_agreement-v0-res.json ├── blimp_anaphor_number_agreement-v0-loglikelihood ├── blimp_anaphor_number_agreement-v0-res.json ├── blimp_animate_subject_passive-v0-loglikelihood ├── blimp_animate_subject_passive-v0-res.json ├── blimp_animate_subject_trans-v0-loglikelihood ├── blimp_animate_subject_trans-v0-res.json ├── blimp_causative-v0-loglikelihood ├── blimp_causative-v0-res.json ├── blimp_complex_NP_island-v0-loglikelihood ├── blimp_complex_NP_island-v0-res.json ├── blimp_coordinate_structure_constraint_complex_left_branch-v0-loglikelihood ├── blimp_coordinate_structure_constraint_complex_left_branch-v0-res.json ├── blimp_coordinate_structure_constraint_object_extraction-v0-loglikelihood ├── blimp_coordinate_structure_constraint_object_extraction-v0-res.json ├── blimp_determiner_noun_agreement_1-v0-loglikelihood ├── blimp_determiner_noun_agreement_1-v0-res.json ├── blimp_determiner_noun_agreement_2-v0-loglikelihood ├── blimp_determiner_noun_agreement_2-v0-res.json ├── blimp_determiner_noun_agreement_irregular_1-v0-loglikelihood ├── blimp_determiner_noun_agreement_irregular_1-v0-res.json ├── blimp_determiner_noun_agreement_irregular_2-v0-loglikelihood ├── blimp_determiner_noun_agreement_irregular_2-v0-res.json ├── blimp_determiner_noun_agreement_with_adj_2-v0-loglikelihood ├── blimp_determiner_noun_agreement_with_adj_2-v0-res.json ├── blimp_determiner_noun_agreement_with_adj_irregular_1-v0-loglikelihood ├── blimp_determiner_noun_agreement_with_adj_irregular_1-v0-res.json ├── blimp_determiner_noun_agreement_with_adj_irregular_2-v0-loglikelihood ├── blimp_determiner_noun_agreement_with_adj_irregular_2-v0-res.json ├── blimp_determiner_noun_agreement_with_adjective_1-v0-loglikelihood ├── blimp_determiner_noun_agreement_with_adjective_1-v0-res.json ├── blimp_distractor_agreement_relational_noun-v0-loglikelihood ├── blimp_distractor_agreement_relational_noun-v0-res.json ├── blimp_distractor_agreement_relative_clause-v0-loglikelihood ├── blimp_distractor_agreement_relative_clause-v0-res.json ├── blimp_drop_argument-v0-loglikelihood ├── blimp_drop_argument-v0-res.json ├── blimp_ellipsis_n_bar_1-v0-loglikelihood ├── blimp_ellipsis_n_bar_1-v0-res.json ├── blimp_ellipsis_n_bar_2-v0-loglikelihood ├── blimp_ellipsis_n_bar_2-v0-res.json ├── blimp_existential_there_object_raising-v0-loglikelihood ├── blimp_existential_there_object_raising-v0-res.json ├── blimp_existential_there_quantifiers_1-v0-loglikelihood ├── blimp_existential_there_quantifiers_1-v0-res.json ├── blimp_existential_there_quantifiers_2-v0-loglikelihood ├── blimp_existential_there_quantifiers_2-v0-res.json ├── blimp_existential_there_subject_raising-v0-loglikelihood ├── blimp_existential_there_subject_raising-v0-res.json ├── blimp_expletive_it_object_raising-v0-loglikelihood ├── blimp_expletive_it_object_raising-v0-res.json ├── blimp_inchoative-v0-loglikelihood ├── blimp_inchoative-v0-res.json ├── blimp_intransitive-v0-loglikelihood ├── blimp_intransitive-v0-res.json ├── blimp_irregular_past_participle_adjectives-v0-loglikelihood ├── blimp_irregular_past_participle_adjectives-v0-res.json ├── blimp_irregular_past_participle_verbs-v0-loglikelihood ├── blimp_irregular_past_participle_verbs-v0-res.json ├── blimp_irregular_plural_subject_verb_agreement_1-v0-loglikelihood ├── blimp_irregular_plural_subject_verb_agreement_1-v0-res.json ├── blimp_irregular_plural_subject_verb_agreement_2-v0-loglikelihood ├── blimp_irregular_plural_subject_verb_agreement_2-v0-res.json ├── blimp_left_branch_island_echo_question-v0-loglikelihood ├── blimp_left_branch_island_echo_question-v0-res.json ├── blimp_left_branch_island_simple_question-v0-loglikelihood ├── blimp_left_branch_island_simple_question-v0-res.json ├── blimp_matrix_question_npi_licensor_present-v0-loglikelihood ├── blimp_matrix_question_npi_licensor_present-v0-res.json ├── blimp_npi_present_1-v0-loglikelihood ├── blimp_npi_present_1-v0-res.json ├── blimp_npi_present_2-v0-loglikelihood ├── blimp_npi_present_2-v0-res.json ├── blimp_only_npi_licensor_present-v0-loglikelihood ├── blimp_only_npi_licensor_present-v0-res.json ├── blimp_only_npi_scope-v0-loglikelihood ├── blimp_only_npi_scope-v0-res.json ├── blimp_passive_1-v0-loglikelihood ├── blimp_passive_1-v0-res.json ├── blimp_passive_2-v0-loglikelihood ├── blimp_passive_2-v0-res.json ├── blimp_principle_A_c_command-v0-loglikelihood ├── blimp_principle_A_c_command-v0-res.json ├── blimp_principle_A_case_1-v0-loglikelihood ├── blimp_principle_A_case_1-v0-res.json ├── blimp_principle_A_case_2-v0-loglikelihood ├── blimp_principle_A_case_2-v0-res.json ├── blimp_principle_A_domain_1-v0-loglikelihood ├── blimp_principle_A_domain_1-v0-res.json ├── blimp_principle_A_domain_2-v0-loglikelihood ├── blimp_principle_A_domain_2-v0-res.json ├── blimp_principle_A_domain_3-v0-loglikelihood ├── blimp_principle_A_domain_3-v0-res.json ├── blimp_principle_A_reconstruction-v0-loglikelihood ├── blimp_principle_A_reconstruction-v0-res.json ├── blimp_regular_plural_subject_verb_agreement_1-v0-loglikelihood ├── blimp_regular_plural_subject_verb_agreement_1-v0-res.json ├── blimp_regular_plural_subject_verb_agreement_2-v0-loglikelihood ├── blimp_regular_plural_subject_verb_agreement_2-v0-res.json ├── blimp_sentential_negation_npi_licensor_present-v0-loglikelihood ├── blimp_sentential_negation_npi_licensor_present-v0-res.json ├── blimp_sentential_negation_npi_scope-v0-loglikelihood ├── blimp_sentential_negation_npi_scope-v0-res.json ├── blimp_sentential_subject_island-v0-loglikelihood ├── blimp_sentential_subject_island-v0-res.json ├── blimp_superlative_quantifiers_1-v0-loglikelihood ├── blimp_superlative_quantifiers_1-v0-res.json ├── blimp_superlative_quantifiers_2-v0-loglikelihood ├── blimp_superlative_quantifiers_2-v0-res.json ├── blimp_tough_vs_raising_1-v0-loglikelihood ├── blimp_tough_vs_raising_1-v0-res.json ├── blimp_tough_vs_raising_2-v0-loglikelihood ├── blimp_tough_vs_raising_2-v0-res.json ├── blimp_transitive-v0-loglikelihood ├── blimp_transitive-v0-res.json ├── blimp_wh_island-v0-loglikelihood ├── blimp_wh_island-v0-res.json ├── blimp_wh_questions_object_gap-v0-loglikelihood ├── blimp_wh_questions_object_gap-v0-res.json ├── blimp_wh_questions_subject_gap-v0-loglikelihood ├── blimp_wh_questions_subject_gap-v0-res.json ├── blimp_wh_questions_subject_gap_long_distance-v0-loglikelihood ├── blimp_wh_questions_subject_gap_long_distance-v0-res.json ├── blimp_wh_vs_that_no_gap-v0-loglikelihood ├── blimp_wh_vs_that_no_gap-v0-res.json ├── blimp_wh_vs_that_no_gap_long_distance-v0-loglikelihood ├── blimp_wh_vs_that_no_gap_long_distance-v0-res.json ├── blimp_wh_vs_that_with_gap-v0-loglikelihood ├── blimp_wh_vs_that_with_gap-v0-res.json ├── blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood ├── blimp_wh_vs_that_with_gap_long_distance-v0-res.json ├── boolq-v0-loglikelihood ├── boolq-v0-res.json ├── boolq-v1-loglikelihood ├── boolq-v1-res.json ├── cb-v0-loglikelihood ├── cb-v0-res.json ├── cb-v1-loglikelihood ├── cb-v1-res.json ├── cola-v0-loglikelihood ├── cola-v0-res.json ├── copa-v0-loglikelihood ├── copa-v0-res.json ├── coqa-v0-greedy_until ├── coqa-v0-res.json ├── coqa-v1-greedy_until ├── coqa-v1-res.json ├── crows_pairs_english-v0-loglikelihood ├── crows_pairs_english-v0-res.json ├── crows_pairs_english_age-v0-loglikelihood ├── crows_pairs_english_age-v0-res.json ├── crows_pairs_english_autre-v0-loglikelihood ├── crows_pairs_english_autre-v0-res.json ├── crows_pairs_english_disability-v0-loglikelihood ├── crows_pairs_english_disability-v0-res.json ├── crows_pairs_english_gender-v0-loglikelihood ├── crows_pairs_english_gender-v0-res.json ├── crows_pairs_english_nationality-v0-loglikelihood ├── crows_pairs_english_nationality-v0-res.json ├── crows_pairs_english_physical_appearance-v0-loglikelihood ├── crows_pairs_english_physical_appearance-v0-res.json ├── crows_pairs_english_race_color-v0-loglikelihood ├── crows_pairs_english_race_color-v0-res.json ├── crows_pairs_english_religion-v0-loglikelihood ├── crows_pairs_english_religion-v0-res.json ├── crows_pairs_english_sexual_orientation-v0-loglikelihood ├── crows_pairs_english_sexual_orientation-v0-res.json ├── crows_pairs_english_socioeconomic-v0-loglikelihood ├── crows_pairs_english_socioeconomic-v0-res.json ├── crows_pairs_french-v0-loglikelihood ├── crows_pairs_french-v0-res.json ├── crows_pairs_french_age-v0-loglikelihood ├── crows_pairs_french_age-v0-res.json ├── crows_pairs_french_autre-v0-loglikelihood ├── crows_pairs_french_autre-v0-res.json ├── crows_pairs_french_disability-v0-loglikelihood ├── crows_pairs_french_disability-v0-res.json ├── crows_pairs_french_gender-v0-loglikelihood ├── crows_pairs_french_gender-v0-res.json ├── crows_pairs_french_nationality-v0-loglikelihood ├── crows_pairs_french_nationality-v0-res.json ├── crows_pairs_french_physical_appearance-v0-loglikelihood ├── crows_pairs_french_physical_appearance-v0-res.json ├── crows_pairs_french_race_color-v0-loglikelihood ├── crows_pairs_french_race_color-v0-res.json ├── crows_pairs_french_religion-v0-loglikelihood ├── crows_pairs_french_religion-v0-res.json ├── crows_pairs_french_sexual_orientation-v0-loglikelihood ├── crows_pairs_french_sexual_orientation-v0-res.json ├── crows_pairs_french_socioeconomic-v0-loglikelihood ├── crows_pairs_french_socioeconomic-v0-res.json ├── cycle_letters-v0-greedy_until ├── cycle_letters-v0-res.json ├── drop-v0-greedy_until ├── drop-v0-res.json ├── drop-v1-greedy_until ├── drop-v1-res.json ├── ethics_cm-v0-loglikelihood ├── ethics_cm-v0-res.json ├── ethics_deontology-v0-loglikelihood ├── ethics_deontology-v0-res.json ├── ethics_justice-v0-loglikelihood ├── ethics_justice-v0-res.json ├── ethics_utilitarianism-v0-loglikelihood ├── ethics_utilitarianism-v0-res.json ├── ethics_utilitarianism_original-v0-loglikelihood ├── ethics_utilitarianism_original-v0-res.json ├── ethics_virtue-v0-loglikelihood ├── ethics_virtue-v0-res.json ├── gpt3_test_0deb8e9bde8e8327bbc48157f638ff3ba06b0cd816dad2beb8ad90f7fbe795c7.pkl ├── gpt3_test_8025023377febbd8c5f2b9f26705c394ff375d0cad7c89c10fd9b8e1eb66ff1c.pkl ├── gpt3_test_bb2cc49115e88788ed870ad0716eb00b280a885f91c7ed6e1e864435e5e2b6ac.pkl ├── gpt3_test_cfd11f555a5a63b6dfa114a55a932e51b724cdd44d4842586b9ce37260bf7aaa.pkl ├── gpt3_test_f307d52964c295e2005c5e782b688c24388e0cecadf29f1e6fc7f394236ea9c0.pkl ├── gsm8k-v0-greedy_until ├── gsm8k-v0-res.json ├── headqa-v0-loglikelihood ├── headqa-v0-res.json ├── headqa_en-v0-loglikelihood ├── headqa_en-v0-res.json ├── headqa_es-v0-loglikelihood ├── headqa_es-v0-res.json ├── hellaswag-v0-loglikelihood ├── hellaswag-v0-res.json ├── hendrycksTest-abstract_algebra-v0-loglikelihood ├── hendrycksTest-abstract_algebra-v0-res.json ├── hendrycksTest-anatomy-v0-loglikelihood ├── hendrycksTest-anatomy-v0-res.json ├── hendrycksTest-astronomy-v0-loglikelihood ├── hendrycksTest-astronomy-v0-res.json ├── hendrycksTest-business_ethics-v0-loglikelihood ├── hendrycksTest-business_ethics-v0-res.json ├── hendrycksTest-clinical_knowledge-v0-loglikelihood ├── hendrycksTest-clinical_knowledge-v0-res.json ├── hendrycksTest-college_biology-v0-loglikelihood ├── hendrycksTest-college_biology-v0-res.json ├── hendrycksTest-college_chemistry-v0-loglikelihood ├── hendrycksTest-college_chemistry-v0-res.json ├── hendrycksTest-college_computer_science-v0-loglikelihood ├── hendrycksTest-college_computer_science-v0-res.json ├── hendrycksTest-college_mathematics-v0-loglikelihood ├── hendrycksTest-college_mathematics-v0-res.json ├── hendrycksTest-college_medicine-v0-loglikelihood ├── hendrycksTest-college_medicine-v0-res.json ├── hendrycksTest-college_physics-v0-loglikelihood ├── hendrycksTest-college_physics-v0-res.json ├── hendrycksTest-computer_security-v0-loglikelihood ├── hendrycksTest-computer_security-v0-res.json ├── hendrycksTest-conceptual_physics-v0-loglikelihood ├── hendrycksTest-conceptual_physics-v0-res.json ├── hendrycksTest-econometrics-v0-loglikelihood ├── hendrycksTest-econometrics-v0-res.json ├── hendrycksTest-electrical_engineering-v0-loglikelihood ├── hendrycksTest-electrical_engineering-v0-res.json ├── hendrycksTest-elementary_mathematics-v0-loglikelihood ├── hendrycksTest-elementary_mathematics-v0-res.json ├── hendrycksTest-formal_logic-v0-loglikelihood ├── hendrycksTest-formal_logic-v0-res.json ├── hendrycksTest-global_facts-v0-loglikelihood ├── hendrycksTest-global_facts-v0-res.json ├── hendrycksTest-high_school_biology-v0-loglikelihood ├── hendrycksTest-high_school_biology-v0-res.json ├── hendrycksTest-high_school_chemistry-v0-loglikelihood ├── hendrycksTest-high_school_chemistry-v0-res.json ├── hendrycksTest-high_school_computer_science-v0-loglikelihood ├── hendrycksTest-high_school_computer_science-v0-res.json ├── hendrycksTest-high_school_european_history-v0-loglikelihood ├── hendrycksTest-high_school_european_history-v0-res.json ├── hendrycksTest-high_school_geography-v0-loglikelihood ├── hendrycksTest-high_school_geography-v0-res.json ├── hendrycksTest-high_school_government_and_politics-v0-loglikelihood ├── hendrycksTest-high_school_government_and_politics-v0-res.json ├── hendrycksTest-high_school_macroeconomics-v0-loglikelihood ├── hendrycksTest-high_school_macroeconomics-v0-res.json ├── hendrycksTest-high_school_mathematics-v0-loglikelihood ├── hendrycksTest-high_school_mathematics-v0-res.json ├── hendrycksTest-high_school_microeconomics-v0-loglikelihood ├── hendrycksTest-high_school_microeconomics-v0-res.json ├── hendrycksTest-high_school_physics-v0-loglikelihood ├── hendrycksTest-high_school_physics-v0-res.json ├── hendrycksTest-high_school_psychology-v0-loglikelihood ├── hendrycksTest-high_school_psychology-v0-res.json ├── hendrycksTest-high_school_statistics-v0-loglikelihood ├── hendrycksTest-high_school_statistics-v0-res.json ├── hendrycksTest-high_school_us_history-v0-loglikelihood ├── hendrycksTest-high_school_us_history-v0-res.json ├── hendrycksTest-high_school_world_history-v0-loglikelihood ├── hendrycksTest-high_school_world_history-v0-res.json ├── hendrycksTest-human_aging-v0-loglikelihood ├── hendrycksTest-human_aging-v0-res.json ├── hendrycksTest-human_sexuality-v0-loglikelihood ├── hendrycksTest-human_sexuality-v0-res.json ├── hendrycksTest-international_law-v0-loglikelihood ├── hendrycksTest-international_law-v0-res.json ├── hendrycksTest-jurisprudence-v0-loglikelihood ├── hendrycksTest-jurisprudence-v0-res.json ├── hendrycksTest-logical_fallacies-v0-loglikelihood ├── hendrycksTest-logical_fallacies-v0-res.json ├── hendrycksTest-machine_learning-v0-loglikelihood ├── hendrycksTest-machine_learning-v0-res.json ├── hendrycksTest-management-v0-loglikelihood ├── hendrycksTest-management-v0-res.json ├── hendrycksTest-marketing-v0-loglikelihood ├── hendrycksTest-marketing-v0-res.json ├── hendrycksTest-medical_genetics-v0-loglikelihood ├── hendrycksTest-medical_genetics-v0-res.json ├── hendrycksTest-miscellaneous-v0-loglikelihood ├── hendrycksTest-miscellaneous-v0-res.json ├── hendrycksTest-moral_disputes-v0-loglikelihood ├── hendrycksTest-moral_disputes-v0-res.json ├── hendrycksTest-moral_scenarios-v0-loglikelihood ├── hendrycksTest-moral_scenarios-v0-res.json ├── hendrycksTest-nutrition-v0-loglikelihood ├── hendrycksTest-nutrition-v0-res.json ├── hendrycksTest-philosophy-v0-loglikelihood ├── hendrycksTest-philosophy-v0-res.json ├── hendrycksTest-prehistory-v0-loglikelihood ├── hendrycksTest-prehistory-v0-res.json ├── hendrycksTest-professional_accounting-v0-loglikelihood ├── hendrycksTest-professional_accounting-v0-res.json ├── hendrycksTest-professional_law-v0-loglikelihood ├── hendrycksTest-professional_law-v0-res.json ├── hendrycksTest-professional_medicine-v0-loglikelihood ├── hendrycksTest-professional_medicine-v0-res.json ├── hendrycksTest-professional_psychology-v0-loglikelihood ├── hendrycksTest-professional_psychology-v0-res.json ├── hendrycksTest-public_relations-v0-loglikelihood ├── hendrycksTest-public_relations-v0-res.json ├── hendrycksTest-security_studies-v0-loglikelihood ├── hendrycksTest-security_studies-v0-res.json ├── hendrycksTest-sociology-v0-loglikelihood ├── hendrycksTest-sociology-v0-res.json ├── hendrycksTest-us_foreign_policy-v0-loglikelihood ├── hendrycksTest-us_foreign_policy-v0-res.json ├── hendrycksTest-virology-v0-loglikelihood ├── hendrycksTest-virology-v0-res.json ├── hendrycksTest-world_religions-v0-loglikelihood ├── hendrycksTest-world_religions-v0-res.json ├── iwslt17-ar-en-v0-greedy_until ├── iwslt17-ar-en-v0-res.json ├── iwslt17-en-ar-v0-greedy_until ├── iwslt17-en-ar-v0-res.json ├── lambada-v0-loglikelihood ├── lambada-v0-res.json ├── lambada_cloze-v0-loglikelihood ├── lambada_cloze-v0-res.json ├── lambada_mt_de-v0-loglikelihood ├── lambada_mt_de-v0-res.json ├── lambada_mt_en-v0-loglikelihood ├── lambada_mt_en-v0-res.json ├── lambada_mt_es-v0-loglikelihood ├── lambada_mt_es-v0-res.json ├── lambada_mt_fr-v0-loglikelihood ├── lambada_mt_fr-v0-res.json ├── lambada_mt_it-v0-loglikelihood ├── lambada_mt_it-v0-res.json ├── lambada_openai-v0-loglikelihood ├── lambada_openai-v0-res.json ├── lambada_openai-v2.0-loglikelihood ├── lambada_openai-v2.0-res.json ├── lambada_openai_cloze-v0-loglikelihood ├── lambada_openai_cloze-v0-res.json ├── lambada_openai_mt_de-v0-loglikelihood ├── lambada_openai_mt_de-v0-res.json ├── lambada_openai_mt_en-v0-loglikelihood ├── lambada_openai_mt_en-v0-res.json ├── lambada_openai_mt_es-v0-loglikelihood ├── lambada_openai_mt_es-v0-res.json ├── lambada_openai_mt_fr-v0-loglikelihood ├── lambada_openai_mt_fr-v0-res.json ├── lambada_openai_mt_it-v0-loglikelihood ├── lambada_openai_mt_it-v0-res.json ├── lambada_standard-v0-loglikelihood ├── lambada_standard-v0-res.json ├── lambada_standard_cloze-v0-loglikelihood ├── lambada_standard_cloze-v0-res.json ├── logiqa-v0-loglikelihood ├── logiqa-v0-res.json ├── math_algebra-v0-greedy_until ├── math_algebra-v0-res.json ├── math_algebra-v1-greedy_until ├── math_algebra-v1-res.json ├── math_counting_and_prob-v0-greedy_until ├── math_counting_and_prob-v0-res.json ├── math_counting_and_prob-v1-greedy_until ├── math_counting_and_prob-v1-res.json ├── math_geometry-v0-greedy_until ├── math_geometry-v0-res.json ├── math_geometry-v1-greedy_until ├── math_geometry-v1-res.json ├── math_intermediate_algebra-v0-greedy_until ├── math_intermediate_algebra-v0-res.json ├── math_intermediate_algebra-v1-greedy_until ├── math_intermediate_algebra-v1-res.json ├── math_num_theory-v0-greedy_until ├── math_num_theory-v0-res.json ├── math_num_theory-v1-greedy_until ├── math_num_theory-v1-res.json ├── math_prealgebra-v0-greedy_until ├── math_prealgebra-v0-res.json ├── math_prealgebra-v1-greedy_until ├── math_prealgebra-v1-res.json ├── math_precalc-v0-greedy_until ├── math_precalc-v0-res.json ├── math_precalc-v1-greedy_until ├── math_precalc-v1-res.json ├── mathqa-v0-loglikelihood ├── mathqa-v0-res.json ├── mc_taco-v0-loglikelihood ├── mc_taco-v0-res.json ├── mnli-v0-loglikelihood ├── mnli-v0-res.json ├── mnli_mismatched-v0-loglikelihood ├── mnli_mismatched-v0-res.json ├── mrpc-v0-loglikelihood ├── mrpc-v0-res.json ├── multirc-v0-loglikelihood ├── multirc-v0-res.json ├── multirc-v1-loglikelihood ├── multirc-v1-res.json ├── mutual-v0-loglikelihood ├── mutual-v0-res.json ├── mutual-v1-loglikelihood ├── mutual-v1-res.json ├── mutual_plus-v0-loglikelihood ├── mutual_plus-v0-res.json ├── mutual_plus-v1-loglikelihood ├── mutual_plus-v1-res.json ├── openbookqa-v0-loglikelihood ├── openbookqa-v0-res.json ├── pile_arxiv-v0-loglikelihood_rolling ├── pile_arxiv-v0-res.json ├── pile_arxiv-v1-loglikelihood_rolling ├── pile_arxiv-v1-res.json ├── pile_bookcorpus2-v0-loglikelihood_rolling ├── pile_bookcorpus2-v0-res.json ├── pile_bookcorpus2-v1-loglikelihood_rolling ├── pile_bookcorpus2-v1-res.json ├── pile_books3-v0-loglikelihood_rolling ├── pile_books3-v0-res.json ├── pile_books3-v1-loglikelihood_rolling ├── pile_books3-v1-res.json ├── pile_dm-mathematics-v0-loglikelihood_rolling ├── pile_dm-mathematics-v0-res.json ├── pile_dm-mathematics-v1-loglikelihood_rolling ├── pile_dm-mathematics-v1-res.json ├── pile_enron-v0-loglikelihood_rolling ├── pile_enron-v0-res.json ├── pile_enron-v1-loglikelihood_rolling ├── pile_enron-v1-res.json ├── pile_europarl-v0-loglikelihood_rolling ├── pile_europarl-v0-res.json ├── pile_europarl-v1-loglikelihood_rolling ├── pile_europarl-v1-res.json ├── pile_freelaw-v0-loglikelihood_rolling ├── pile_freelaw-v0-res.json ├── pile_freelaw-v1-loglikelihood_rolling ├── pile_freelaw-v1-res.json ├── pile_github-v0-loglikelihood_rolling ├── pile_github-v0-res.json ├── pile_github-v1-loglikelihood_rolling ├── pile_github-v1-res.json ├── pile_gutenberg-v0-loglikelihood_rolling ├── pile_gutenberg-v0-res.json ├── pile_gutenberg-v1-loglikelihood_rolling ├── pile_gutenberg-v1-res.json ├── pile_hackernews-v0-loglikelihood_rolling ├── pile_hackernews-v0-res.json ├── pile_hackernews-v1-loglikelihood_rolling ├── pile_hackernews-v1-res.json ├── pile_nih-exporter-v0-loglikelihood_rolling ├── pile_nih-exporter-v0-res.json ├── pile_nih-exporter-v1-loglikelihood_rolling ├── pile_nih-exporter-v1-res.json ├── pile_opensubtitles-v0-loglikelihood_rolling ├── pile_opensubtitles-v0-res.json ├── pile_opensubtitles-v1-loglikelihood_rolling ├── pile_opensubtitles-v1-res.json ├── pile_openwebtext2-v0-loglikelihood_rolling ├── pile_openwebtext2-v0-res.json ├── pile_openwebtext2-v1-loglikelihood_rolling ├── pile_openwebtext2-v1-res.json ├── pile_philpapers-v0-loglikelihood_rolling ├── pile_philpapers-v0-res.json ├── pile_philpapers-v1-loglikelihood_rolling ├── pile_philpapers-v1-res.json ├── pile_pile-cc-v0-loglikelihood_rolling ├── pile_pile-cc-v0-res.json ├── pile_pile-cc-v1-loglikelihood_rolling ├── pile_pile-cc-v1-res.json ├── pile_pubmed-abstracts-v0-loglikelihood_rolling ├── pile_pubmed-abstracts-v0-res.json ├── pile_pubmed-abstracts-v1-loglikelihood_rolling ├── pile_pubmed-abstracts-v1-res.json ├── pile_pubmed-central-v0-loglikelihood_rolling ├── pile_pubmed-central-v0-res.json ├── pile_pubmed-central-v1-loglikelihood_rolling ├── pile_pubmed-central-v1-res.json ├── pile_stackexchange-v0-loglikelihood_rolling ├── pile_stackexchange-v0-res.json ├── pile_stackexchange-v1-loglikelihood_rolling ├── pile_stackexchange-v1-res.json ├── pile_ubuntu-irc-v0-loglikelihood_rolling ├── pile_ubuntu-irc-v0-res.json ├── pile_ubuntu-irc-v1-loglikelihood_rolling ├── pile_ubuntu-irc-v1-res.json ├── pile_uspto-v0-loglikelihood_rolling ├── pile_uspto-v0-res.json ├── pile_uspto-v1-loglikelihood_rolling ├── pile_uspto-v1-res.json ├── pile_wikipedia-v0-loglikelihood_rolling ├── pile_wikipedia-v0-res.json ├── pile_wikipedia-v1-loglikelihood_rolling ├── pile_wikipedia-v1-res.json ├── pile_youtubesubtitles-v0-loglikelihood_rolling ├── pile_youtubesubtitles-v0-res.json ├── pile_youtubesubtitles-v1-loglikelihood_rolling ├── pile_youtubesubtitles-v1-res.json ├── piqa-v0-loglikelihood ├── piqa-v0-res.json ├── prost-v0-loglikelihood ├── prost-v0-res.json ├── pubmedqa-v0-loglikelihood ├── pubmedqa-v0-res.json ├── qa4mre_2011-v0-loglikelihood ├── qa4mre_2011-v0-res.json ├── qa4mre_2012-v0-loglikelihood ├── qa4mre_2012-v0-res.json ├── qa4mre_2013-v0-loglikelihood ├── qa4mre_2013-v0-res.json ├── qnli-v0-loglikelihood ├── qnli-v0-res.json ├── qqp-v0-loglikelihood ├── qqp-v0-res.json ├── race-v0-loglikelihood ├── race-v0-res.json ├── random_insertion-v0-greedy_until ├── random_insertion-v0-res.json ├── record-v0-loglikelihood ├── record-v0-res.json ├── reversed_words-v0-greedy_until ├── reversed_words-v0-res.json ├── rte-v0-loglikelihood ├── rte-v0-res.json ├── sciq-v0-loglikelihood ├── sciq-v0-res.json ├── squad2-v0-greedy_until ├── squad2-v0-loglikelihood ├── squad2-v0-res.json ├── squad2-v1-greedy_until ├── squad2-v1-loglikelihood ├── squad2-v1-res.json ├── sst-v0-loglikelihood ├── sst-v0-res.json ├── swag-v0-loglikelihood ├── swag-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 ├── toxigen-v0-loglikelihood ├── toxigen-v0-res.json ├── triviaqa-v0-loglikelihood ├── triviaqa-v0-res.json ├── triviaqa-v1-loglikelihood ├── triviaqa-v1-res.json ├── truthfulqa_gen-v0-greedy_until ├── truthfulqa_gen-v0-res.json ├── truthfulqa_gen-v1-greedy_until ├── truthfulqa_gen-v1-res.json ├── truthfulqa_mc-v0-loglikelihood ├── truthfulqa_mc-v0-res.json ├── truthfulqa_mc-v1-loglikelihood ├── truthfulqa_mc-v1-res.json ├── webqs-v0-loglikelihood ├── webqs-v0-res.json ├── wic-v0-loglikelihood ├── wic-v0-res.json ├── wikitext-v0-loglikelihood_rolling ├── wikitext-v0-res.json ├── wikitext-v1-loglikelihood_rolling ├── wikitext-v1-res.json ├── winogrande-v0-loglikelihood ├── winogrande-v0-res.json ├── wmt14-en-fr-v0-greedy_until ├── wmt14-en-fr-v0-res.json ├── wmt14-fr-en-v0-greedy_until ├── wmt14-fr-en-v0-res.json ├── wmt16-de-en-v0-greedy_until ├── wmt16-de-en-v0-res.json ├── wmt16-en-de-v0-greedy_until ├── wmt16-en-de-v0-res.json ├── wmt16-en-ro-v0-greedy_until ├── wmt16-en-ro-v0-res.json ├── wmt16-ro-en-v0-greedy_until ├── wmt16-ro-en-v0-res.json ├── wmt20-cs-en-v0-greedy_until ├── wmt20-cs-en-v0-res.json ├── wmt20-de-en-v0-greedy_until ├── wmt20-de-en-v0-res.json ├── wmt20-de-fr-v0-greedy_until ├── wmt20-de-fr-v0-res.json ├── wmt20-en-cs-v0-greedy_until ├── wmt20-en-cs-v0-res.json ├── wmt20-en-de-v0-greedy_until ├── wmt20-en-de-v0-res.json ├── wmt20-en-iu-v0-greedy_until ├── wmt20-en-iu-v0-res.json ├── wmt20-en-ja-v0-greedy_until ├── wmt20-en-ja-v0-res.json ├── wmt20-en-ja-v1-greedy_until ├── wmt20-en-ja-v1-res.json ├── wmt20-en-km-v0-greedy_until ├── wmt20-en-km-v0-res.json ├── wmt20-en-pl-v0-greedy_until ├── wmt20-en-pl-v0-res.json ├── wmt20-en-ps-v0-greedy_until ├── wmt20-en-ps-v0-res.json ├── wmt20-en-ru-v0-greedy_until ├── wmt20-en-ru-v0-res.json ├── wmt20-en-ta-v0-greedy_until ├── wmt20-en-ta-v0-res.json ├── wmt20-en-zh-v0-greedy_until ├── wmt20-en-zh-v0-res.json ├── wmt20-en-zh-v1-greedy_until ├── wmt20-en-zh-v1-res.json ├── wmt20-fr-de-v0-greedy_until ├── wmt20-fr-de-v0-res.json ├── wmt20-iu-en-v0-greedy_until ├── wmt20-iu-en-v0-res.json ├── wmt20-ja-en-v0-greedy_until ├── wmt20-ja-en-v0-res.json ├── wmt20-km-en-v0-greedy_until ├── wmt20-km-en-v0-res.json ├── wmt20-pl-en-v0-greedy_until ├── wmt20-pl-en-v0-res.json ├── wmt20-ps-en-v0-greedy_until ├── wmt20-ps-en-v0-res.json ├── wmt20-ru-en-v0-greedy_until ├── wmt20-ru-en-v0-res.json ├── wmt20-ta-en-v0-greedy_until ├── wmt20-ta-en-v0-res.json ├── wmt20-zh-en-v0-greedy_until ├── wmt20-zh-en-v0-res.json ├── wnli-v0-loglikelihood ├── wnli-v0-res.json ├── wnli-v1-loglikelihood ├── wnli-v1-res.json ├── wsc-v0-loglikelihood ├── wsc-v0-res.json ├── wsc273-v0-loglikelihood └── wsc273-v0-res.json ├── tests_master ├── test_description.py ├── test_generate_13_grams.py ├── test_models.py └── test_version_stable.py └── utils.py /doc/figs/demo_gen.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/doc/figs/demo_gen.gif -------------------------------------------------------------------------------- /doc/figs/privatelora.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/doc/figs/privatelora.png -------------------------------------------------------------------------------- /experiments/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/experiments/.DS_Store -------------------------------------------------------------------------------- /experiments/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/experiments/__init__.py -------------------------------------------------------------------------------- /experiments/infras/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/experiments/infras/__init__.py -------------------------------------------------------------------------------- /lm-evaluation-harness/.flake8: -------------------------------------------------------------------------------- 1 | [flake8] 2 | ignore = E203, E266, E501, W503, F403, F401, C901 3 | max-line-length = 127 4 | max-complexity = 10 5 | select = B,C,E,F,W,T4,B9 6 | -------------------------------------------------------------------------------- /lm-evaluation-harness/CODEOWNERS: -------------------------------------------------------------------------------- 1 | * @haileyschoelkopf @lintangsutawika 2 | -------------------------------------------------------------------------------- /lm-evaluation-harness/docs/img/fewshot_example_gpt3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/docs/img/fewshot_example_gpt3.png -------------------------------------------------------------------------------- /lm-evaluation-harness/ignore.txt: -------------------------------------------------------------------------------- 1 | ROUGE 2 | rouge 3 | nin 4 | maka 5 | mor 6 | te 7 | ond 8 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/__init__.py: -------------------------------------------------------------------------------- 1 | from .evaluator import evaluate, simple_evaluate 2 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/api/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/lm_eval/api/__init__.py -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/decontamination/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/lm_eval/decontamination/__init__.py -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/anli/anli_r2.yaml: -------------------------------------------------------------------------------- 1 | include: anli_r1.yaml 2 | task: anli_r2 3 | training_split: train_r2 4 | validation_split: dev_r2 5 | test_split: test_r2 6 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/anli/anli_r3.yaml: -------------------------------------------------------------------------------- 1 | include: anli_r1.yaml 2 | task: anli_r3 3 | training_split: train_r3 4 | validation_split: dev_r3 5 | test_split: test_r3 6 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arc/arc_challenge.yaml: -------------------------------------------------------------------------------- 1 | include: arc_easy.yaml 2 | task: arc_challenge 3 | dataset_name: ARC-Challenge 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_2da.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_2da 3 | dataset_name: arithmetic_2da 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_2dm.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_2dm 3 | dataset_name: arithmetic_2dm 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_2ds.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_2ds 3 | dataset_name: arithmetic_2ds 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_3da.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_3da 3 | dataset_name: arithmetic_3da 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_3ds.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_3ds 3 | dataset_name: arithmetic_3ds 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_4da.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_4da 3 | dataset_name: arithmetic_4da 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_4ds.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_4ds 3 | dataset_name: arithmetic_4ds 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_5da.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_5da 3 | dataset_name: arithmetic_5da 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/arithmetic/arithmetic_5ds.yaml: -------------------------------------------------------------------------------- 1 | include: arithmetic_1dc.yaml 2 | task: arithmetic_5ds 3 | dataset_name: arithmetic_5ds 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/benchmarks/flan/flan_held_in.yaml: -------------------------------------------------------------------------------- 1 | group: flan_held_in 2 | task: 3 | - flan_boolq 4 | - flan_rte 5 | - flan_anli 6 | - flan_arc 7 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/anachronisms.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: anachronisms_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_anachronisms_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/arithmetic.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: arithmetic_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_arithmetic_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/auto_debugging.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: auto_debugging_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_auto_debugging_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/bbq_lite_json.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: bbq_lite_json_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_bbq_lite_json_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/codenames.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: codenames_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_codenames_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/color.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: color_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_color_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/crash_blossom.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: crash_blossom_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_crash_blossom_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/crass_ai.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: crass_ai_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_crass_ai_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/cryptonite.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: cryptonite_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_cryptonite_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/cs_algorithms.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: cs_algorithms_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_cs_algorithms_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/disfl_qa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: disfl_qa_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_disfl_qa_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/dyck_languages.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: dyck_languages_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_dyck_languages_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/emoji_movie.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: emoji_movie_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_emoji_movie_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/fact_checker.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: fact_checker_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_fact_checker_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/few_shot_nlg.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: few_shot_nlg_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_few_shot_nlg_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/gem.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: gem_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_gem_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/hhh_alignment.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: hhh_alignment_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_hhh_alignment_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/hyperbaton.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: hyperbaton_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_hyperbaton_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/implicatures.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: implicatures_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_implicatures_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/kanji_ascii.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: kanji_ascii_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_kanji_ascii_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/kannada.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: kannada_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_kannada_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/key_value_maps.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: key_value_maps_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_key_value_maps_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/known_unknowns.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: known_unknowns_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_known_unknowns_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/language_games.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: language_games_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_language_games_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/list_functions.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: list_functions_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_list_functions_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/logical_args.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: logical_args_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_logical_args_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/matrixshapes.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: matrixshapes_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_matrixshapes_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/misconceptions.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: misconceptions_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_misconceptions_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/mnist_ascii.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: mnist_ascii_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_mnist_ascii_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/multiemo.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: multiemo_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_multiemo_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/navigate.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: navigate_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_navigate_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/novel_concepts.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: novel_concepts_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_novel_concepts_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/odd_one_out.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: odd_one_out_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_odd_one_out_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/operators.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: operators_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_operators_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/parsinlu_qa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: parsinlu_qa_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_parsinlu_qa_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/persian_idioms.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: persian_idioms_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_persian_idioms_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/physics.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: physics_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_physics_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/qa_wikidata.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: qa_wikidata_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_qa_wikidata_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/rephrase.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: rephrase_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_rephrase_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/riddle_sense.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: riddle_sense_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_riddle_sense_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/ruin_names.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: ruin_names_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_ruin_names_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/snarks.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: snarks_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_snarks_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/social_iqa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: social_iqa_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_social_iqa_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/social_support.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: social_support_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_social_support_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/strategyqa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: strategyqa_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_strategyqa_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/suicide_risk.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: suicide_risk_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_suicide_risk_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/tense.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: tense_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_tense_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/timedial.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: timedial_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_timedial_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/topical_chat.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: topical_chat_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_topical_chat_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/winowhy.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: winowhy_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_winowhy_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/greedy_until/word_sorting.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: word_sorting_zero_shot 3 | include: ../greedy_until_template_yaml 4 | task: bigbench_word_sorting_greedy_until 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/arithmetic.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: arithmetic_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_arithmetic_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/codenames.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: codenames_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_codenames_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/color.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: color_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_color_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/crass_ai.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: crass_ai_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_crass_ai_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/cryptonite.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: cryptonite_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_cryptonite_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/disfl_qa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: disfl_qa_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_disfl_qa_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/emoji_movie.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: emoji_movie_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_emoji_movie_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/gem.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: gem_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_gem_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/hyperbaton.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: hyperbaton_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_hyperbaton_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: kanji_ascii_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_kanji_ascii_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/kannada.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: kannada_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_kannada_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: mnist_ascii_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_mnist_ascii_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: multiemo_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_multiemo_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/navigate.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: navigate_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_navigate_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/odd_one_out.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: odd_one_out_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_odd_one_out_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/operators.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: operators_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_operators_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/parsinlu_qa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: parsinlu_qa_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_parsinlu_qa_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/physics.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: physics_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_physics_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/qa_wikidata.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: qa_wikidata_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_qa_wikidata_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/rephrase.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: rephrase_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_rephrase_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/ruin_names.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: ruin_names_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_ruin_names_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/snarks.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: snarks_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_snarks_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: social_iqa_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_social_iqa_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/strategyqa.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: strategyqa_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_strategyqa_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/tense.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: tense_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_tense_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/timedial.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: timedial_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_timedial_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/bigbench/multiple_choice/winowhy.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: winowhy_zero_shot 3 | include: ../multiple_choice_template_yaml 4 | task: bigbench_winowhy_multiple_choice 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/adjunct_island.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: adjunct_island 3 | include: template_yaml 4 | task: blimp_adjunct_island 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: anaphor_gender_agreement 3 | include: template_yaml 4 | task: blimp_anaphor_gender_agreement 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/anaphor_number_agreement.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: anaphor_number_agreement 3 | include: template_yaml 4 | task: blimp_anaphor_number_agreement 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/animate_subject_passive.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: animate_subject_passive 3 | include: template_yaml 4 | task: blimp_animate_subject_passive 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/animate_subject_trans.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: animate_subject_trans 3 | include: template_yaml 4 | task: blimp_animate_subject_trans 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/causative.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: causative 3 | include: template_yaml 4 | task: blimp_causative 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/complex_NP_island.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: complex_NP_island 3 | include: template_yaml 4 | task: blimp_complex_NP_island 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: determiner_noun_agreement_1 3 | include: template_yaml 4 | task: blimp_determiner_noun_agreement_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: determiner_noun_agreement_2 3 | include: template_yaml 4 | task: blimp_determiner_noun_agreement_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/drop_argument.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: drop_argument 3 | include: template_yaml 4 | task: blimp_drop_argument 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: ellipsis_n_bar_1 3 | include: template_yaml 4 | task: blimp_ellipsis_n_bar_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: ellipsis_n_bar_2 3 | include: template_yaml 4 | task: blimp_ellipsis_n_bar_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/existential_there_object_raising.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: existential_there_object_raising 3 | include: template_yaml 4 | task: blimp_existential_there_object_raising 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: existential_there_quantifiers_1 3 | include: template_yaml 4 | task: blimp_existential_there_quantifiers_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: existential_there_quantifiers_2 3 | include: template_yaml 4 | task: blimp_existential_there_quantifiers_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/existential_there_subject_raising.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: existential_there_subject_raising 3 | include: template_yaml 4 | task: blimp_existential_there_subject_raising 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/expletive_it_object_raising.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: expletive_it_object_raising 3 | include: template_yaml 4 | task: blimp_expletive_it_object_raising 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/inchoative.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: inchoative 3 | include: template_yaml 4 | task: blimp_inchoative 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/intransitive.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: intransitive 3 | include: template_yaml 4 | task: blimp_intransitive 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: irregular_past_participle_verbs 3 | include: template_yaml 4 | task: blimp_irregular_past_participle_verbs 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: left_branch_island_echo_question 3 | include: template_yaml 4 | task: blimp_left_branch_island_echo_question 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/npi_present_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: npi_present_1 3 | include: template_yaml 4 | task: blimp_npi_present_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/npi_present_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: npi_present_2 3 | include: template_yaml 4 | task: blimp_npi_present_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/only_npi_licensor_present.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: only_npi_licensor_present 3 | include: template_yaml 4 | task: blimp_only_npi_licensor_present 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/only_npi_scope.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: only_npi_scope 3 | include: template_yaml 4 | task: blimp_only_npi_scope 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/passive_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: passive_1 3 | include: template_yaml 4 | task: blimp_passive_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/passive_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: passive_2 3 | include: template_yaml 4 | task: blimp_passive_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/principle_A_c_command.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: principle_A_c_command 3 | include: template_yaml 4 | task: blimp_principle_A_c_command 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/principle_A_case_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: principle_A_case_1 3 | include: template_yaml 4 | task: blimp_principle_A_case_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/principle_A_case_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: principle_A_case_2 3 | include: template_yaml 4 | task: blimp_principle_A_case_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/principle_A_domain_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: principle_A_domain_1 3 | include: template_yaml 4 | task: blimp_principle_A_domain_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/principle_A_domain_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: principle_A_domain_2 3 | include: template_yaml 4 | task: blimp_principle_A_domain_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/principle_A_domain_3.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: principle_A_domain_3 3 | include: template_yaml 4 | task: blimp_principle_A_domain_3 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/principle_A_reconstruction.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: principle_A_reconstruction 3 | include: template_yaml 4 | task: blimp_principle_A_reconstruction 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: sentential_negation_npi_scope 3 | include: template_yaml 4 | task: blimp_sentential_negation_npi_scope 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/sentential_subject_island.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: sentential_subject_island 3 | include: template_yaml 4 | task: blimp_sentential_subject_island 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: superlative_quantifiers_1 3 | include: template_yaml 4 | task: blimp_superlative_quantifiers_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: superlative_quantifiers_2 3 | include: template_yaml 4 | task: blimp_superlative_quantifiers_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/tough_vs_raising_1.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: tough_vs_raising_1 3 | include: template_yaml 4 | task: blimp_tough_vs_raising_1 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/tough_vs_raising_2.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: tough_vs_raising_2 3 | include: template_yaml 4 | task: blimp_tough_vs_raising_2 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/transitive.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: transitive 3 | include: template_yaml 4 | task: blimp_transitive 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/wh_island.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: wh_island 3 | include: template_yaml 4 | task: blimp_wh_island 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/wh_questions_object_gap.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: wh_questions_object_gap 3 | include: template_yaml 4 | task: blimp_wh_questions_object_gap 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: wh_questions_subject_gap 3 | include: template_yaml 4 | task: blimp_wh_questions_subject_gap 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: wh_vs_that_no_gap 3 | include: template_yaml 4 | task: blimp_wh_vs_that_no_gap 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: wh_vs_that_no_gap_long_distance 3 | include: template_yaml 4 | task: blimp_wh_vs_that_no_gap_long_distance 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: wh_vs_that_with_gap 3 | include: template_yaml 4 | task: blimp_wh_vs_that_with_gap 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: wh_vs_that_with_gap_long_distance 3 | include: template_yaml 4 | task: blimp_wh_vs_that_with_gap_long_distance 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/ceval/ceval-valid_accountant.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "accountant" 2 | "description": "以下是中国关于注册会计师的单项选择题，请选出其中的正确答案。\n\n" 3 | "include": "_default_ceval_yaml" 4 | "task": "ceval-valid_accountant" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/ceval/ceval-valid_art_studies.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "art_studies" 2 | "description": "以下是中国关于艺术学的单项选择题，请选出其中的正确答案。\n\n" 3 | "include": "_default_ceval_yaml" 4 | "task": "ceval-valid_art_studies" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/ceval/ceval-valid_law.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "law" 2 | "description": "以下是中国关于法学的单项选择题，请选出其中的正确答案。\n\n" 3 | "include": "_default_ceval_yaml" 4 | "task": "ceval-valid_law" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/ceval/ceval-valid_logic.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "logic" 2 | "description": "以下是中国关于逻辑学的单项选择题，请选出其中的正确答案。\n\n" 3 | "include": "_default_ceval_yaml" 4 | "task": "ceval-valid_logic" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/ceval/ceval-valid_marxism.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "marxism" 2 | "description": "以下是中国关于马克思主义基本原理的单项选择题，请选出其中的正确答案。\n\n" 3 | "include": "_default_ceval_yaml" 4 | "task": "ceval-valid_marxism" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/ceval/ceval-valid_physician.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "physician" 2 | "description": "以下是中国关于医师资格的单项选择题，请选出其中的正确答案。\n\n" 3 | "include": "_default_ceval_yaml" 4 | "task": "ceval-valid_physician" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_agronomy.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "agronomy" 2 | "description": "以下是关于农学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_agronomy" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_anatomy.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "anatomy" 2 | "description": "以下是关于解剖学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_anatomy" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_arts.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "arts" 2 | "description": "以下是关于艺术学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_arts" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_astronomy.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "astronomy" 2 | "description": "以下是关于天文学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_astronomy" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_law.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "college_law" 2 | "description": "以下是关于大学法律的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_college_law" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_economics.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "economics" 2 | "description": "以下是关于经济学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_economics" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_education.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "education" 2 | "description": "以下是关于教育学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_education" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_ethnology.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "ethnology" 2 | "description": "以下是关于民族学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_ethnology" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_food_science.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "food_science" 2 | "description": "以下是关于食品科学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_food_science" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_genetics.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "genetics" 2 | "description": "以下是关于遗传学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_genetics" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_global_facts.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "global_facts" 2 | "description": "以下是关于全球事实的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_global_facts" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_journalism.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "journalism" 2 | "description": "以下是关于新闻学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_journalism" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_jurisprudence.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "jurisprudence" 2 | "description": "以下是关于法理学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_jurisprudence" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_logical.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "logical" 2 | "description": "以下是关于逻辑学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_logical" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_management.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "management" 2 | "description": "以下是关于管理学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_management" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_marketing.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "marketing" 2 | "description": "以下是关于市场营销的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_marketing" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_nutrition.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "nutrition" 2 | "description": "以下是关于营养学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_nutrition" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_philosophy.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "philosophy" 2 | "description": "以下是关于哲学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_philosophy" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_sociology.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "sociology" 2 | "description": "以下是关于社会学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_sociology" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_virology.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "virology" 2 | "description": "以下是关于病毒学的单项选择题，请直接给出正确答案的选项。\n\n" 3 | "include": "_default_template_yaml" 4 | "task": "cmmlu_virology" 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_english_age.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_english_age 3 | dataset_name: english 4 | process_docs: !function utils.filter_age 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_english_autre.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_english_autre 3 | dataset_name: english 4 | process_docs: !function utils.filter_autre 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_english_gender.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_english_gender 3 | dataset_name: english 4 | process_docs: !function utils.filter_gender 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_english_religion.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_english_religion 3 | dataset_name: english 4 | process_docs: !function utils.filter_religion 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french 3 | dataset_name: french 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french_age.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french_age 3 | dataset_name: french 4 | process_docs: !function utils.filter_age 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french_autre.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french_autre 3 | dataset_name: french 4 | process_docs: !function utils.filter_autre 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french_disability.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french_disability 3 | dataset_name: french 4 | process_docs: !function utils.filter_disability 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french_gender.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french_gender 3 | dataset_name: french 4 | process_docs: !function utils.filter_gender 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french_race_color.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french_race_color 3 | dataset_name: french 4 | process_docs: !function utils.filter_race_color 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french_religion.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french_religion 3 | dataset_name: french 4 | process_docs: !function utils.filter_religion 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/crows_pairs/crows_pairs_french_socioeconomic.yaml: -------------------------------------------------------------------------------- 1 | include: crows_pairs_english.yaml 2 | task: crows_pairs_french_socioeconomic 3 | dataset_name: french 4 | process_docs: !function utils.filter_socio 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/csatqa/csatqa_gr.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "GR" 2 | "include": "_default_csatqa_yaml" 3 | "task": "csatqa_gr" 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/csatqa/csatqa_li.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "LI" 2 | "include": "_default_csatqa_yaml" 3 | "task": "csatqa_li" 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/csatqa/csatqa_rch.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "RCH" 2 | "include": "_default_csatqa_yaml" 3 | "task": "csatqa_rch" 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/csatqa/csatqa_rcs.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "RCS" 2 | "include": "_default_csatqa_yaml" 3 | "task": "csatqa_rcs" 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/csatqa/csatqa_rcss.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "RCSS" 2 | "include": "_default_csatqa_yaml" 3 | "task": "csatqa_rcss" 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/csatqa/csatqa_wr.yaml: -------------------------------------------------------------------------------- 1 | "dataset_name": "WR" 2 | "include": "_default_csatqa_yaml" 3 | "task": "csatqa_wr" 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/glue/mnli/mismatch.yaml: -------------------------------------------------------------------------------- 1 | include: default.yaml 2 | task: mnli_mismatch 3 | validation_split: validation_mismatched 4 | test_split: test_mismatched 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/headqa/headqa_es.yaml: -------------------------------------------------------------------------------- 1 | include: headqa_en.yaml 2 | task: headqa_es 3 | dataset_name: es 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/lambada_multilingual/lambada_mt_de.yaml: -------------------------------------------------------------------------------- 1 | include: lambada_mt_en.yaml 2 | task: lambada_openai_mt_de 3 | dataset_name: de 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/lambada_multilingual/lambada_mt_es.yaml: -------------------------------------------------------------------------------- 1 | include: lambada_mt_en.yaml 2 | task: lambada_openai_mt_es 3 | dataset_name: es 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/lambada_multilingual/lambada_mt_fr.yaml: -------------------------------------------------------------------------------- 1 | include: lambada_mt_en.yaml 2 | task: lambada_openai_mt_fr 3 | dataset_name: fr 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/lambada_multilingual/lambada_mt_it.yaml: -------------------------------------------------------------------------------- 1 | include: lambada_mt_en.yaml 2 | task: lambada_openai_mt_it 3 | dataset_name: it 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/minerva_math/minerva_math_counting_and_prob.yaml: -------------------------------------------------------------------------------- 1 | include: minerva_math_algebra.yaml 2 | dataset_name: counting_and_probability 3 | task: minerva_math_counting_and_prob 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/minerva_math/minerva_math_geometry.yaml: -------------------------------------------------------------------------------- 1 | include: minerva_math_algebra.yaml 2 | dataset_name: geometry 3 | task: minerva_math_geometry 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/minerva_math/minerva_math_intermediate_algebra.yaml: -------------------------------------------------------------------------------- 1 | include: minerva_math_algebra.yaml 2 | dataset_name: intermediate_algebra 3 | task: minerva_math_intermediate_algebra 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/minerva_math/minerva_math_num_theory.yaml: -------------------------------------------------------------------------------- 1 | include: minerva_math_algebra.yaml 2 | dataset_name: number_theory 3 | task: minerva_math_num_theory 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/minerva_math/minerva_math_prealgebra.yaml: -------------------------------------------------------------------------------- 1 | include: minerva_math_algebra.yaml 2 | dataset_name: prealgebra 3 | task: minerva_math_prealgebra 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/minerva_math/minerva_math_precalc.yaml: -------------------------------------------------------------------------------- 1 | include: minerva_math_algebra.yaml 2 | dataset_name: precalculus 3 | task: minerva_math_precalc 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/mutual/multual_plus.yaml: -------------------------------------------------------------------------------- 1 | include: mutual.yaml 2 | task: mutual_plus 3 | dataset_name: mutual_plus 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/nq_open/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/lm_eval/tasks/nq_open/README.md -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_bookcorpus2.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_bookcorpus2 3 | dataset_name: pile_bookcorpus2 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_books3.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_books3 3 | dataset_name: pile_books3 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_dm-mathematics.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_dm-mathematics 3 | dataset_name: pile_dm-mathematics 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_enron.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_enron 3 | dataset_name: pile_enron 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_europarl.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_europarl 3 | dataset_name: pile_europarl 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_freelaw.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_freelaw 3 | dataset_name: pile_freelaw 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_github.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_github 3 | dataset_name: pile_github 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_gutenberg.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_gutenberg 3 | dataset_name: pile_gutenberg 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_hackernews.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_hackernews 3 | dataset_name: pile_hackernews 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_nih-exporter.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_nih-exporter 3 | dataset_name: pile_nih-exporter 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_opensubtitles.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_opensubtitles 3 | dataset_name: pile_opensubtitles 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_openwebtext2.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_openwebtext2 3 | dataset_name: pile_openwebtext2 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_philpapers.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_philpapers 3 | dataset_name: pile_philpapers 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_pile-cc.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_pile-cc 3 | dataset_name: pile_pile-cc 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_pubmed-abstracts.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_pubmed-abstracts 3 | dataset_name: pile_pubmed-abstracts 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_pubmed-central.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_pubmed-central 3 | dataset_name: pile_pubmed-central 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_stackexchange.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_stackexchange 3 | dataset_name: pile_stackexchange 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_ubuntu-irc.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_ubuntu-irc 3 | dataset_name: pile_ubuntu-irc 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_uspto.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_uspto 3 | dataset_name: pile_uspto 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_wikipedia.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_wikipedia 3 | dataset_name: pile_wikipedia 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/pile/pile_youtubesubtitles.yaml: -------------------------------------------------------------------------------- 1 | include: pile_arxiv.yaml 2 | task: pile_youtubesubtitles 3 | dataset_name: pile_youtubesubtitles 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/polemo2/polemo2_out.yaml: -------------------------------------------------------------------------------- 1 | include: polemo2_in.yaml 2 | task: polemo2_out 3 | dataset_path: allegro/klej-polemo2-out 4 | dataset_name: klej-polemo2-out 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/qa4mre/qa4mre_2012.yaml: -------------------------------------------------------------------------------- 1 | include: qa4mre_2011.yaml 2 | task: qa4mre_2012 3 | dataset_path: qa4mre 4 | dataset_name: 2012.main.EN 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/qa4mre/qa4mre_2013.yaml: -------------------------------------------------------------------------------- 1 | include: qa4mre_2011.yaml 2 | task: qa4mre_2013 3 | dataset_path: qa4mre 4 | dataset_name: 2013.main.EN 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/squadv2/with_noans_prob.yaml: -------------------------------------------------------------------------------- 1 | group: squadv2_complete 2 | task: 3 | - squadv2 4 | - squadv2_noans_loglikelihood 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/toxigen/utils.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | 4 | def doc_to_target(doc): 5 | return np.round(((doc["toxicity_ai"] + doc["toxicity_human"]) > 5.5), 0).astype( 6 | np.int32 7 | ) 8 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_ht.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_ht 3 | dataset_name: ht 4 | doc_to_text: !function utils.doc_to_text_ht 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_id.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_id 3 | dataset_name: id 4 | doc_to_text: !function utils.doc_to_text_id 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_it.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_it 3 | dataset_name: it 4 | doc_to_text: !function utils.doc_to_text_it 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_qu.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_qu 3 | dataset_name: qu 4 | doc_to_text: !function utils.doc_to_text_qu 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_sw.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_sw 3 | dataset_name: sw 4 | doc_to_text: !function utils.doc_to_text_sw 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_ta.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_ta 3 | dataset_name: ta 4 | doc_to_text: !function utils.doc_to_text_ta 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_th.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_th 3 | dataset_name: th 4 | doc_to_text: !function utils.doc_to_text_th 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_tr.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_tr 3 | dataset_name: tr 4 | doc_to_text: !function utils.doc_to_text_tr 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_vi.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_vi 3 | dataset_name: vi 4 | doc_to_text: !function utils.doc_to_text_vi 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xcopa/default_zh.yaml: -------------------------------------------------------------------------------- 1 | include: default_et.yaml 2 | task: xcopa_zh 3 | dataset_name: zh 4 | doc_to_text: !function utils.doc_to_text_zh 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_en.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_en 3 | dataset_name: en 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_es.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_es 3 | dataset_name: es 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_eu.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_eu 3 | dataset_name: eu 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_hi.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_hi 3 | dataset_name: hi 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_id.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_id 3 | dataset_name: id 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_my.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_my 3 | dataset_name: my 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_ru.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_ru 3 | dataset_name: ru 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_sw.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_sw 3 | dataset_name: sw 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_te.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_te 3 | dataset_name: te 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xstorycloze/default_zh.yaml: -------------------------------------------------------------------------------- 1 | include: default_ar.yaml 2 | task: xstorycloze_zh 3 | dataset_name: zh 4 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xwinograd/xwinograd_en.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: en 3 | include: xwinograd_common_yaml 4 | task: xwinograd_en 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xwinograd/xwinograd_fr.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: fr 3 | include: xwinograd_common_yaml 4 | task: xwinograd_fr 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xwinograd/xwinograd_jp.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: jp 3 | include: xwinograd_common_yaml 4 | task: xwinograd_jp 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xwinograd/xwinograd_pt.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: pt 3 | include: xwinograd_common_yaml 4 | task: xwinograd_pt 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xwinograd/xwinograd_ru.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: ru 3 | include: xwinograd_common_yaml 4 | task: xwinograd_ru 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/lm_eval/tasks/xwinograd/xwinograd_zh.yaml: -------------------------------------------------------------------------------- 1 | # Generated by utils.py 2 | dataset_name: zh 3 | include: xwinograd_common_yaml 4 | task: xwinograd_zh 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/requirements.txt: -------------------------------------------------------------------------------- 1 | -e . 2 | -------------------------------------------------------------------------------- /lm-evaluation-harness/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/scripts/__init__.py -------------------------------------------------------------------------------- /lm-evaluation-harness/scripts/clean_training_data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/scripts/clean_training_data/__init__.py -------------------------------------------------------------------------------- /lm-evaluation-harness/setup.py: -------------------------------------------------------------------------------- 1 | import setuptools 2 | 3 | # This is to make sure that the package supports editable installs 4 | setuptools.setup() 5 | -------------------------------------------------------------------------------- /lm-evaluation-harness/templates/new_yaml_task/blank_yaml.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/templates/new_yaml_task/blank_yaml.yaml -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alipay/private_llm/33e45c629e07b266e5274e0f1148452a3a07c072/lm-evaluation-harness/tests/__init__.py -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anagrams1-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 7c0c5246d3f751f39119a5629ac1d4b2c6fd2a315f78d6de9b2c387e24e3fef1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anagrams1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anagrams1": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"anagrams1": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anagrams2-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 6700a3c44e48abe8337238dcbe3b54cf4abafe0c204c52d921e590872fbd05e7 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anagrams2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anagrams2": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"anagrams2": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anli_r1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3a84baf2f170e138c6ce0bc9f06f905def35d705fa2b8781f10c87aef404c4cb -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anli_r1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anli_r1": {"acc": 0.334, "acc_stderr": 0.014922019523732967}}, "versions": {"anli_r1": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anli_r2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d0ea3c3e09d533982c15b4c034439896d6af4bbafb2254d305e20215534a251d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anli_r2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anli_r2": {"acc": 0.356, "acc_stderr": 0.015149042659306628}}, "versions": {"anli_r2": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anli_r3-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6b6e5c6a794f2fbff78b7aa24fe0c90156039334bbd1cb34f7af9fc6e6183845 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/anli_r3-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anli_r3": {"acc": 0.31916666666666665, "acc_stderr": 0.01346230971200514}}, "versions": {"anli_r3": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arc_challenge-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 41c34c96cca8ace661911d0033d630c554b283f5a3953bcdc50720ae6b00a9c1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arc_challenge-v2.0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8ebbbc510644ede7bf53496c381e276d5a1eec14828870e8b7e611f231e6d5f6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arc_easy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ffa6e39a35a16299dcb015f17f986aaa598ad8b4840c4cebe0339a7042232741 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_1dc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 04c3a63a6b3c579bd3775d92b3076ba9130041d5ce7cf9244d3f86e95c804387 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_1dc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_1dc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_1dc": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_2da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6ca1ca6ebd7cac4420d5005f7f35b0edbc921377f5e4f8874cc176e4fb6d79d4 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_2da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_2da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2da": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_2dm-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 14ac5e510cdf82967d6827a9ca059906ee1db2e347be1b17f36403a157e73552 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_2dm-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_2dm": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2dm": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_2ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 66f7ff3b40251ee38fadcbee658e309a200224356fc3efa07d0a490a2c24bfa3 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_2ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_2ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2ds": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_3da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c421f9cd5a5001b80e528441da925128177a04db8526ebcdab543a90b33c9ce2 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_3da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_3da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_3da": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_3ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d3d8bad8827d4530945a1d8b3c7589c0235bbed0bc89e7561a6fdac678f6ce5c -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_3ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_3ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_3ds": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_4da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d3557beb8b9e5704122c2fc6362b11fbe2c3f2f3cb72aed4462b208767c40e01 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_4da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_4da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_4da": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_4ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d915830b8621e66331383bb2ae4c60acebf008e2f94741092ef4c33ea5441037 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_4ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_4ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_4ds": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_5da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 49edb1e735660631ea6cc309721e6c0b80b7106a613a6959514852ca48f1130e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_5da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_5da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_5da": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_5ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2888d6d098a5ef8c1e7f0d8295ba80826e2e04e431f57508dfb71d53e1cd4604 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/arithmetic_5ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_5ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_5ds": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_adjunct_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 976a5cac4bdb724632eebd4cb9e522203ce3da8d5525288a597c86e80469f3f2 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_anaphor_gender_agreement-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2d8964e56a17661502ecf3f09c0befba63915360ddf2145b0bd845816950515d -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_anaphor_number_agreement-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0bdad31c974ba064e1f1ba931841ec2ba7461e8b0ca54ea5f79f08b6bae0bab5 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_animate_subject_passive-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 064c38fcd072b8bd12f54ea4f8e41599ed4e11dc386e93b77e1fc07967d1f960 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_animate_subject_trans-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2a84231e7b79f517427e57e2099c88fed3d60a7efab4ef9506e263b4091d5cfa -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_causative-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3d67ad025185dbb0808ebd7f508edcb5750c18fc3c01ad91f20fda80780c916c -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_causative-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_causative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_causative": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_complex_NP_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f46cfcc7e43050a235fd2a6b989cabbfbcce76786df74db9f0d4a9cd1caa1628 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7e1cc5b9f71abfbe56c4bdf343a1e5632785b66a986b8e904a41ed8f45a2c33e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_coordinate_structure_constraint_object_extraction-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 23ddafdff7b1ebe331b146e23b2c21aa109fe57aa1ce8ca201a0d239fcbdd166 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2df8cc7f17089f7e8c7d974dcb324c809d30ef059a5be22aed6b69f44230809f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 123e2acd00fbba60aba1fbae607c79a062e512c9e79c7d8dfafff63e30111d76 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_irregular_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7fab9f02e71a224ae7931aa77f8a9a61d887a7480756adc965d4746e97fb04a5 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ddb24ddfaebe076b3aa7107937d71bf5f4503a78283bc889e39200368603681e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 95acb74fac7d57ae2c9d208361a5f8ad36b0b19a055f02e648ed8e99505f4b43 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ad61c619aa79433d02f1aeacde2ab87291fd5d5c370032c24d41c4f0065ed1f9 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ccc64b4d5e80c081d5161aae5828212ba49d277ca8c5a4281f181744727a6a99 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adjective_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 007c47e5fbf88119c5180feef75e1345d448e56adcd4c7ab2d52fb8d67350d34 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_distractor_agreement_relational_noun-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8aab641bd5933f84f46a14f5c1208a3c855cace7e67b44abcd5aff8fec96717d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_distractor_agreement_relative_clause-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bf78e2b53c0f3531303c668c96bd3897a0a35e960da37439e63724ecba4e371a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_drop_argument-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 616109e63f162dcd31a632943e7ef0c9e0431afeb179e83e9b04b39007b16f5b -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_ellipsis_n_bar_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d14e4b7fcdd68991eb39b9cf3ade4b37dee9ddd39b688f861d81a327e47a969f -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_ellipsis_n_bar_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0523771a217759f0b22b89807694ee7f6381ce98a584b1fd070ba96194a3273b -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_existential_there_object_raising-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 63567712076256f373131971676c1c6d711efef73cd0e4de3cc639bc631a2413 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_existential_there_quantifiers_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d77594382e6d9af31a8b8ef00ba1ef6c29d6be6d0ddb7a9c27ef25ace654e05a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_existential_there_quantifiers_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6e6add7baff4217f383425bef58288202018e041b24084edcaa5df8af08f820c -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_existential_there_subject_raising-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9b324b28ae3e1b5d49ecf4b7b2a16c7bbc8ff38d000cf216fab75df633da2084 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_expletive_it_object_raising-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ceede5b38248a62125a74a8332602b8eac5ef40864f071ad8d86e7971e07219d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_inchoative-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3ff73629fb4473986a0e8ae2fcb7c40e88292189ab0d8755d20836c5aa5a2f99 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_inchoative-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_inchoative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_inchoative": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_intransitive-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6469ae3b0d46b008846b5fd132f2d2b26ea2858745d056df1470b89aa97a790f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_intransitive-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_intransitive": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_intransitive": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_irregular_past_participle_adjectives-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 47c56f336df11924d8b97feb46339ce55bea4b216b6fd13946cc999ea36a4a95 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_irregular_past_participle_verbs-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 63ec733873f94ace71cb34112d1c3cd5bb768c26b975fb90acc9b8ba3f4e938e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_irregular_plural_subject_verb_agreement_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7084358b1b7dd7fb5ead1a58f4b499d6f7610eca897bfac25a986d0f9a91aa5d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_irregular_plural_subject_verb_agreement_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9534751f83a86b6cbe1fb12fb9feb827b0b7836a663108928b4ecc1d70b08871 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_left_branch_island_echo_question-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9852b38612db8c6adf938a5d8a7a9e5ce9e655259d6cc806b142506fcaff0ed4 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_left_branch_island_simple_question-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6cb36bbdae7754f8832f50872c3dd511ce12547e00fa0771deb747be3355eb85 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_matrix_question_npi_licensor_present-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a3a702a3335c79b02b36caf37c68069050c2a8a3a03c3610c09afc39d2b83fb1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_npi_present_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3ef532a85e0ee8f8ff779bc7ddc873d515969a708da84a4eb4a85b7c843cf244 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_npi_present_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fdb688ac6259bb65d234ef0a36e9a9ee449f9608f633b12e1943b462aead8e17 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_only_npi_licensor_present-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d2d0711611b5b218c6fa8c7278494749252b7868c396451919b761303556bd66 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_only_npi_scope-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fc0be817478c212327050fa297ef61ad214f4847dbff61d4e0fe7914c06a1691 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_passive_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fa4addddd8e380031b8e0871776cabcb707c0f21dcaf5d8b3defec66cce55043 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_passive_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 755bdfe2c89737c43001ff1dc83d68ad33e444aaf0669af66aaf82dcd09f2eca -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_principle_A_c_command-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7c2ed82612af9175052cd44d8e178b6dd084c04eb462a3d88fcacfad2df8be8e -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_principle_A_case_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 49d2b8ce6667a6166fdc2a2e5dbe7ff07d9b8415e9f33482aef15956b3ebc24a -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_principle_A_case_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cd68adb65c891d672e22bf53c054b2083ab08bc1da43951732b409c942d14bc7 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_principle_A_domain_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 290e7eddacea4ec16989af697f2ee3373fdd9aef4b452bf887184c6e2f6e7d9d -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_principle_A_domain_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | eb5ddf0a97982373ab1a4e58267cfcdebdecdb86c376dfd5ebf46737c9d3ee12 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_principle_A_domain_3-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 38454befedcf1f3f6ef27d3bef9ccfdfb3e94a7ab32d86a63493a920d2d50093 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_principle_A_reconstruction-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 894efedfd8750d5b8de6157f9b2ed2b51b5290d3a78ea9b041fc62d34e96efbc -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_regular_plural_subject_verb_agreement_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5bc0441f31e32443cf761bca6e961d504e1e84b15aa4e1d79e5c8ed5b4c2aa3a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_regular_plural_subject_verb_agreement_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f69d9891f59872538962221fccc425b07df7cfbd83cdc546ce83e6b0e9a93f7c -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_sentential_negation_npi_licensor_present-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e6666c5657215ff4bfd646b8ee3ae6df956e71c0be9ab1c287fb1b68291dd0d1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_sentential_negation_npi_scope-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 32fcbd0a1c6e664af2751bad552587b5ca3911973b07f4fb2cf0a2acd3de5349 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_sentential_subject_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 80f5f98fad26240de2767fe58c4b18d864df41cbfa76f06c84c3fce9f14f4833 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_superlative_quantifiers_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8a01f6a5ea87a01c0c9b0c7b3bc4de4711bf0ff050976976651182b9ed34a0d4 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_superlative_quantifiers_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 59c20ff0f632cf42afc74ecc682cf92e5e740417b01e6cf9a610a3bc544d2ea5 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_tough_vs_raising_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 973fe56534fdef1207f0fc08dd09a210304c55f33c6cbb17552754bf54f11c86 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_tough_vs_raising_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d255a10a34f14d77d9526604a17b0f6747d32f62fc2e3a09e9ab10054535fd45 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_transitive-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d0d47fe40a7ee558ba782edbc4f49f7d9123c8472a36decc97f8ab142b45b9d8 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_transitive-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_transitive": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_transitive": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 91a9e4b60b0f3572a7fdbd7648d0e69f36e5eb34db715315b0082558d7ed8b65 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_questions_object_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4d4aaa0274ccd485ff8430ed61b8f83806febe18c16616c7d050f637a0463eba -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_questions_subject_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d5486ffcc075cad4302e37ece9bbf5b2063c0b5a48e76c8e1dd365e22a5a48fc -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_questions_subject_gap_long_distance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 37483dfda688b62ad27161c9fc1e1e7710c5a6e6a7cd3474df119bcafd30e97f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_vs_that_no_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d1d3e439b2020ef5ed232bfebbcc9634adc5117e9eb61e38fdbbe2c8ea128d54 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_vs_that_no_gap_long_distance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a142cc2a6fcd93230b650927b07367cad957b8f3f42cb4072151da53dea301df -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_vs_that_with_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d41a9b85e4c31e445bf9b46b8642df02203ccc02b4a9b254bf76066d5c54b4b7 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | eed67491bdf493a1dad8f1d9766bc7bd0e79946365b833c0f7eb81ac998e3dca -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/boolq-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | de5aa6f77a2e0fd050b9c272f10c4d5d5581e4f75ffa60926f79e60ae1738960 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/boolq-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/boolq-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 6577e0d88572772ef08e64f624c0e3df0953286ae1f118ccef15623b59ffeabf -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/boolq-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cb-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ec3b1bbb9561e39c43c6f77a23b4060b15c606141c5346e3d0791b3e92aaa5d0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cb-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cb-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 77b11f4348eb8a7f57faf95c531fda01ab4bf0e729f91a82451ed8e71ec8e66d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cb-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cola-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e8635578ed8ee70b707a666d35e468b9321db24470f80c92080651e2bfa01751 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cola-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cola": {"mcc": -0.04538802810223175, "mcc_stderr": 0.023100371589225246}}, "versions": {"cola": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/copa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 66276b9045b5300cba4b81340db06f674f031fa0b8883714ad0d03be464cd799 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/copa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"copa": {"acc": 0.48, "acc_stderr": 0.050211673156867795}}, "versions": {"copa": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/coqa-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 4a8605d5deed0423ec095700251ed93325b45d320aca35d4ce1e94702094435e -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/coqa-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 57581470b921435d40da97872bb1cfda6ecf963ccc4b0240a3b04e3fea8c8e3a -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ee3ce1ddb8071d4189e5b06e7f3c618a434221ac52935d0f434c4d183f01458a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_age-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | de74d2ac7f926f2f486c045d84aae8f71711102f9d77b31f758fd148810d13d3 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_autre-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a197ccc8538231404a8e43f5ed0fbbfb2c317b4da337f6e7aa9642131aeb426a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_disability-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 90c1bcfdeec0ff51d891ee8cf00ae2a5ec61bab6739faea9865809b8ffed2cdb -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_gender-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2bf62b7cc678f64ffad4a6e6715ff76a2b984bfe8d1165da4b76b3b4dfafb2f9 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_nationality-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b85bc849811ccfa9971a6ee3fca7342752c314c0cb6f126e10d9ec4d0450c541 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_physical_appearance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d1823f5038afafa7a5338e42531720480c8ccf4e177789526caf294d52d56e89 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_race_color-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0a750596d77cd96502dc414ff699a399b1b91c2078adeec1d3dd982b3d591089 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_religion-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2ed57377174adaf0fb30037eb055eafdd02cd46e57bc32066d5fecd90a14b6e1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_sexual_orientation-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e754a309296b157677dfba6e6feef983d1ce38dd0169ae726265621a7b573163 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_english_socioeconomic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c309eabfd247a702e32efc4e08211f9a72693d38995be5dd444d497b476396bd -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4fb61dcf4d2c59d6470b297a01d5f429ee442864e225e1760fbf191b2a0901cd -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_age-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b14a5769f415a234abe89063a1b546aa4a990c84217e5d4a697874cd7f85af35 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_autre-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f145ad5086da0bf8c76f0730258529fa243efe32b7ab792d3c4716284b4b5495 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_disability-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fa1e5fc7492a66c9a90765e605003c38408347617db5ecf36706f1d374af5d42 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_gender-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 010b8404655911c86555616da23afffce9dc3981e1acbbfdb022d9c474430209 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_nationality-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 146eb60c8796fe3f25307a6776337f0b077b58ce02edec64c99df4b906c19b9f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_physical_appearance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ea61eaad64e9292790d4bbef955ffeebed7a595de098bc5ac726a6e51f27f9af -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_race_color-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6f9119026abff33c5c882d6172e092e806a8b21bd86864022978b1961839350f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_religion-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8af6445eeb634dad5f0723e40615afe993e1e3f129a4f314fe4117e633c2efd3 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_sexual_orientation-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2ce823fdb93d325aa8fb40db5d335b093b4b69792763532d940a752440ee3a76 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/crows_pairs_french_socioeconomic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8ba0a525c65f795c99f6416e70c998e75e4b6cc43bf9a4bd7ccacd3c3591e9cb -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cycle_letters-v0-greedy_until: -------------------------------------------------------------------------------- 1 | eb23f7d5de7528eefd8ed5f8054c402ff947319cccfef7195995946f99389201 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/cycle_letters-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cycle_letters": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"cycle_letters": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/drop-v0-greedy_until: -------------------------------------------------------------------------------- 1 | ca566c630d8ac853d5785d4b5c40a5137172c34b48af3350e1f79e6d548b36ba -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/drop-v1-greedy_until: -------------------------------------------------------------------------------- 1 | a670f911ab2999d72db15f534b22703d19e7837edbda4f9f199ad587f7aae6b2 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_cm-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 92d136ebb2bd86cd036e61699ad9a1417dbb48651f0a3afa5045cf57cef5a3f6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_cm-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_cm": {"acc": 0.49987129987129986, "acc_stderr": 0.008022881531793336}}, "versions": {"ethics_cm": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_deontology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 74ecebe322457d70afc16fde848978410a09b854dc65c47f428d100bd1593248 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_justice-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d7dfc44fea507b5c5c3a8218f79ed8197da8599ebb396d85feb91c25512126b6 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_utilitarianism-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 88872f1ed1b203f9649a4ced4fb4627d18c17af455d713de6e17c05eced4ec60 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_utilitarianism-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_utilitarianism": {"acc": 0.49771214642262895, "acc_stderr": 0.007211546310787838}}, "versions": {"ethics_utilitarianism": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_utilitarianism_original-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5b42ba1faf5ece6a6ec9a3976ce79c1fac8df5b98272aab85457188c2142693c -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/ethics_virtue-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8021db8de46850090ddae6e6ec2d382029c3027b7c69884607503f916d09b709 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/gsm8k-v0-greedy_until: -------------------------------------------------------------------------------- 1 | e7292dbdd7fd8419ba954f2e0701e04c8d0e8842fe053dbf2fe47d926630e35e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/gsm8k-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"gsm8k": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"gsm8k": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/headqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/headqa_en-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 09da45119b12a0144e3081f8fb790c2a22af7b9c3aac42f54423d348a711fbf5 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/headqa_es-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hellaswag-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | abb808c97d6529eda6c11067837a132c62d25cba0394d720f80cca6df9f7196e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-abstract_algebra-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e35d1eeb356ac1084d4e9773f028cb3c81ba1c6e5574d598ac4a78aa467cd797 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-anatomy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bf05e04ed8cf61cf3aad294ed3f5a16137775ffdd20f1b129022ddffc1251768 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-astronomy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bed1e47127cc2893c6aef63b9a0909cca31aa351a703da2a166b01cae03c3311 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-business_ethics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b3b27e9dbad587377d3c8cab1072782de883e245da93a563bd8b3099017b1fc0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-clinical_knowledge-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fbcb7ce507e0675d811e71e10a67c8d05a6605e29036f46776e04a6588cefbda -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-college_biology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c29e4e67ff91af29b9434884874414d1b1b32ccc32903c6b1639469b19907419 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-college_chemistry-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 044752b21540db95118b8cbe7e75c4c9b8758e27df56543deaeadec7f749a28d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-college_computer_science-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4ea26ad780290429ac5a3317559c154848d662bd40532c966458ba6f2a32d0a3 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-college_mathematics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e9fe80752686527281f834d2397875b4580581434b94799f9de6aaa450bd73ff -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-college_medicine-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | dd6e0a9be1407890e9f8cd4434fb6aa4752ab3d2473837fd465ad99f60ad685e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-college_physics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 704a7671ef981fb95594782bc446dd632e87ebdbe89436a0603b714fb5786c75 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-computer_security-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a8a1892d1906cc3e7ffd321043f0a60f3b8b69ef76e5c6ff03c6ea41dc87d0cb -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-conceptual_physics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 622f191ccfc7a597d99f39897ebe3f95a9ddce0e662fcfb411aa554b289bb355 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-econometrics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cde76ba2c7382b4876e17136c94f52aca2774e50342ab757b2a2d18da370dcb6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-electrical_engineering-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b9b5d8b8bb02696302ec6bc2a99bf987a5504d3bae0e529d2c8f263538c97518 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-elementary_mathematics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6b21f5cd5606268421a667152ec989424b66905c02adbab8d4ff6bb9d21b77d1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-formal_logic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c0d0f0c008a5f3faf2f6f4268d87bbc09c40bb66ae08cf38eea0bf2e519c5a59 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-global_facts-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9fdc85240b8170839278b1e883ee0868611d84dce202cb8aa037c841ec76d089 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_biology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d4dc051f37a49dc75c218741e87bc826fd44f31ee1309b55e0f33bd191c1bc78 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_chemistry-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f4f338e45415c4b5ee7f1d249155bcd910c8401bd1436760a5ec61cb6bb211b6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_computer_science-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 870d5a6300c527077aaf6baa3e750e75fa840b41657cf82549f39b768b14862d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_european_history-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d8070e113be9d420fef5578cb69c70df4ea5118f9b18553023fd9efd5ff0b7f4 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_geography-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | add45970ea3865be7c7a31f788a835949f6937ac73f699b122ca56a3431e95f8 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_government_and_politics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 11f40d8f48ba5cd739e21d54c3c04d3761f81df5cb7ddd77df868d24ced44b49 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_macroeconomics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ce4faae2fb6628caa48f6fc74cbc848880db49e6ff51079392778a2322bcefef -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_mathematics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ab368d16fc4648ad27940f71abd266366663f51db612f732a0b9b0eea28de9f8 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_microeconomics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 513b998585ebc1ebdefca6435b7c84fd73dc36fc80321a22503467f04efed23e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_physics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | dae59e82d3d4d8dec82239d9620b72cc47bb6efbe2f1c2f9b9d23e849c9c5e32 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_psychology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0e4c8d13806d3696167e40544d2d114c557c10c74bc61fcb9c51bbfced0266ef -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_statistics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 33d1d6eaaa2c3a944bf49d3f220a4efc328d7c3b3465b7cec40ae36d8984b75f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_us_history-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8c65c1a28330dd001d395ac11f1bb80c3b33f5935f503e74067aef6e9e1d9d9b -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-high_school_world_history-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 1c8b994bd9a63ec874fc8d0e3a27077118b7adc472306b2fd6c55635a78b9d52 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-human_aging-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0880b3a78f8d7b17ffc612031427b9085367cf65dabe2a68c4b64e3171d17e88 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-human_sexuality-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4b07922fa1d549b655c21440b13d869263ce7dd9771d8147c450f11c91d26c10 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-international_law-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ea9b2cefd27959db564168f6ad1169a5eaa012fc5a5d5b8faf9e34d94e335dc1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-jurisprudence-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cac440189f1ec778e82f4975d88b74689553ecc5116aaa7f76587a50c1a610e0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-logical_fallacies-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2e9449dd803f9e2334dc562d9f04031fd013ed36b883b44ab500533a5dbbface -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-machine_learning-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7a7138821a66ef946e427b40344cf7f1a916a2926995a85ef731a3bee40cb7ce -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-management-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 355489f4bd176ab84db5ef4c03d56ddeeeb1b0ad69827122b2d800e1cdc7e5f0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-marketing-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b4fa0681fe54671a80509779d4338d744097a7206687f62977df7145dfa74a66 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-medical_genetics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | db6141246889a19dd3f6b9109f314d49c1a70f7a98795858804378b095c4a2fe -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-miscellaneous-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 972dd88dbbaf09d14766e243cfc233425e7c01a26dbc61bdb9eeefa788822331 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-moral_disputes-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d6ef028022c02b69d1516973e08bebaa14d8debcf2589a2bb124823178202d20 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-moral_scenarios-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a8e1882e77728b53c8b86312254d08320d8363fb606d746a8dd145b812f62cf5 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-nutrition-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 19e49d218f55ed5ec4bd1a6cd3f3388c6f620b81484e7abe8b298e5481c3044d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-philosophy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a419204da36c2b7a70fa8909a3a804260cc3283c7e07917534dfb76216c77f46 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-prehistory-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6983c560a562749f4f702249a3a6ae51fa495acc0643a980bf2cf52c6c5d4b95 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-professional_accounting-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 847418f7b22cd9b499e95fd73c40a2fbc40076895280cc2c560199c0c4c4f433 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-professional_law-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c38c9d5d84eeb7a5f3c4a34d6e70d7e15847b3c38f26e4b119c982bb935e118f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-professional_medicine-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7a30599858398169cde61430c18efdd7fb4dcd09c34aa9baba70f0f8cf17a9f1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-professional_psychology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 92a5fad6e9ec700f84946faeccd399dda3569fb71837c9fb0c5c87f5ec29c43e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-public_relations-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ab70f500cf24e876f6ae6bdc27525a1d6074fa9b6ea97770255d9fc2559b36ff -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-security_studies-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 92dfffe2acf3278256486d3e1cf1edb5a739ad0a54c0f9c67695f7a411ed5f76 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-sociology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f99a3caece11169f2a5cc951001f92027104afd25d29b2a399883bd4bf118605 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-us_foreign_policy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a1a338d0083a21054f74d36a296d6bd8e2e457327c0fd630bebcc61ed758044d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-virology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0ffa491f7bad2abbb64ecd752a295729167599b3815238cab0ecf4cb08bba9b6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/hendrycksTest-world_religions-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 97a0f68ba30ea3a6ef1db1a2925c964b09ecc54455a0a930da083e52677815bd -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/iwslt17-ar-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | e94d310de91fad7ce36f4cf3305552020221482c5588f2efcefaa019893504f1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/iwslt17-en-ar-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b20adbcd2c6d135e28600b427113532c5df624cb3a90e8c5e48715c09a3a38fa -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_cloze-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7655e748b63ae7e9911411d2d2a2577221d6c861ca4448509992541294d689f3 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_mt_de-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5ad125e1708499832b2cee8c3388f89f9c0277010fd96fbd3359039ce8105984 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_mt_en-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_mt_es-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4a88f4b316c72fe0396c382d6cbb33568ac4d0ad225150d3536635c085359fc9 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_mt_fr-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5d16f4a0c51dc6d7b6df2ebeba2bbfa51e700b843779b559b3d90183d7b02a11 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_mt_it-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fd87c6c5cf4e0499c5f9f80e5bd7ee6a4f3d2991902a0cc3ec9e6eaf22d6760a -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai-v2.0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9ca5643bbaafed2f027eab5b68cc438e9e268f6df9a678e956e61726a985cf0b -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai-v2.0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai": "2.0"}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai_cloze-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7655e748b63ae7e9911411d2d2a2577221d6c861ca4448509992541294d689f3 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai_mt_de-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5ad125e1708499832b2cee8c3388f89f9c0277010fd96fbd3359039ce8105984 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai_mt_en-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai_mt_es-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4a88f4b316c72fe0396c382d6cbb33568ac4d0ad225150d3536635c085359fc9 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai_mt_fr-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5d16f4a0c51dc6d7b6df2ebeba2bbfa51e700b843779b559b3d90183d7b02a11 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_openai_mt_it-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fd87c6c5cf4e0499c5f9f80e5bd7ee6a4f3d2991902a0cc3ec9e6eaf22d6760a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_standard-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8958d9f8d8145046b692fadd8a9cc9c8bad5617c10774280cf7c24c21d2be160 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/lambada_standard_cloze-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b604f00bc9f2a77ef41f8cfdb5a8509b3ae9266893b9e90abc665f5399ecba4e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/logiqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 12495c50454ba5e1ce0753bd18c09aaca516bebd27648d815e37b15229dbf198 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_algebra-v0-greedy_until: -------------------------------------------------------------------------------- 1 | f19182ce697a2c095d9e5b56ee6659dc38c93994b69ca75d7c3d3f5fd87572b4 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_algebra-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_algebra": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_algebra-v1-greedy_until: -------------------------------------------------------------------------------- 1 | f19182ce697a2c095d9e5b56ee6659dc38c93994b69ca75d7c3d3f5fd87572b4 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_algebra-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_algebra": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_counting_and_prob-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 2aa9ae43ee9dbb2457525247d7b65358632c5eaa9cbfc40cf95a4f17f5d942ad -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_counting_and_prob-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 2aa9ae43ee9dbb2457525247d7b65358632c5eaa9cbfc40cf95a4f17f5d942ad -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_geometry-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 46bc4cb219b6903397da782699a684bdbb982c0c954ff82e6beeed5c84878f42 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_geometry-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_geometry": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_geometry": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_geometry-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 46bc4cb219b6903397da782699a684bdbb982c0c954ff82e6beeed5c84878f42 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_geometry-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_geometry": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_geometry": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_intermediate_algebra-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d53c699de272d517ed7ad783b4e692302be9f9f97a8d4ac7a6541e538a7cabe0 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_intermediate_algebra-v1-greedy_until: -------------------------------------------------------------------------------- 1 | d53c699de272d517ed7ad783b4e692302be9f9f97a8d4ac7a6541e538a7cabe0 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_num_theory-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b920ccb507afdcf3ef6f4c04891913731e9f32ec914801791c6d9f8abf6e1897 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_num_theory-v1-greedy_until: -------------------------------------------------------------------------------- 1 | b920ccb507afdcf3ef6f4c04891913731e9f32ec914801791c6d9f8abf6e1897 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_prealgebra-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_prealgebra-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_prealgebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_prealgebra": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_prealgebra-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_prealgebra-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_prealgebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_prealgebra": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_precalc-v0-greedy_until: -------------------------------------------------------------------------------- 1 | bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_precalc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_precalc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_precalc": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_precalc-v1-greedy_until: -------------------------------------------------------------------------------- 1 | bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/math_precalc-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_precalc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_precalc": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mathqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a45260e49f02c7cb8886b3746db4d388890860b202dd8a9f0267e3c324e0af13 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mc_taco-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 1811808ef05afd5f30ffc3471622a3dd7a1b681b17a2f7616695ad6b2a45943c -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mc_taco-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mc_taco": {"em": 0.07732732732732733, "f1": 0.41600515965511614}}, "versions": {"mc_taco": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mnli-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4fc7b56b8f1e37e38f4a052b227baec2df914c898c3405d3e994726ba4fba976 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mnli-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mnli": {"acc": 0.32868059093224655, "acc_stderr": 0.004741640290753859}}, "versions": {"mnli": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mnli_mismatched-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3784acf322e79f31702a7a0612030e4ba5c4fc466ad976a34ee3f3d7278c01f0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mnli_mismatched-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mnli_mismatched": {"acc": 0.3360455655004068, "acc_stderr": 0.004763973908606819}}, "versions": {"mnli_mismatched": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mrpc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9f54cbff8d6accba99cfa2c4c4b359563313941018173d7dcf9e32dc28c06583 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/multirc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cdb026c027437a8b4653212d0944d36fc16f49921dcb8e4bef899d15a55e9f80 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/multirc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"multirc": {"acc": 0.07450157397691501, "acc_stderr": 0.008510441526175931}}, "versions": {"multirc": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/multirc-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 0e793bd6f637a70a04c6f2cda080188fc037961b2f909095fe63f7bdbc4a90c6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/multirc-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"multirc": {"acc": 0.046169989506820566, "acc_stderr": 0.006801377886208738}}, "versions": {"multirc": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mutual-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mutual-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mutual_plus-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/mutual_plus-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/openbookqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 78a49a0ca1a47373adb33463b1d092e6bc0d8f4b01bcb380ada48065037849d7 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_arxiv-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_arxiv-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_bookcorpus2-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_bookcorpus2-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_books3-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f8f36f705b999b6d55fa72ff89a82793dd1cb568ab1f8727a6a2086a12b9410 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_books3-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f8f36f705b999b6d55fa72ff89a82793dd1cb568ab1f8727a6a2086a12b9410 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_dm-mathematics-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d5b7967c0ece8b816f3921a8bd0fad23365349e935b491595e2ad1135af42da6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_dm-mathematics-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d5b7967c0ece8b816f3921a8bd0fad23365349e935b491595e2ad1135af42da6 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_enron-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4baa6ccdc9e3aa9921675ab4400d5e89d7b546b844a8ea28f6461d649066418a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_enron-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4baa6ccdc9e3aa9921675ab4400d5e89d7b546b844a8ea28f6461d649066418a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_europarl-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e67d3dbccd47d308bfc5b0e66b76d0dfc5e386ebfa94e056562c2281c395543f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_europarl-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e67d3dbccd47d308bfc5b0e66b76d0dfc5e386ebfa94e056562c2281c395543f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_freelaw-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d77f3f68aadd6cbf1290c2f6737b2ed5d5c2a60e4c81a65c280f207783caabe1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_freelaw-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d77f3f68aadd6cbf1290c2f6737b2ed5d5c2a60e4c81a65c280f207783caabe1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_github-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | df384c3df3d8f53273e97127c5bb84c17e638acad7d6bc9c91f6dee96d43b639 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_github-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | df384c3df3d8f53273e97127c5bb84c17e638acad7d6bc9c91f6dee96d43b639 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_gutenberg-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 02a559f74a9105145e7d4d9c5ddea372b5b4938f5368dc8ffafc39cbe3b4c7ef -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_gutenberg-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 02a559f74a9105145e7d4d9c5ddea372b5b4938f5368dc8ffafc39cbe3b4c7ef -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_hackernews-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ec1082ee5a5326e0d57aa4e73b634937140c1de9af95f154e8ab57b05d9b422b -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_hackernews-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ec1082ee5a5326e0d57aa4e73b634937140c1de9af95f154e8ab57b05d9b422b -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_nih-exporter-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 520ea6e04e8a39dc0b5f63a837429a78a40e63d39d109096101feb8c5b2cf8d8 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_nih-exporter-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 520ea6e04e8a39dc0b5f63a837429a78a40e63d39d109096101feb8c5b2cf8d8 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_opensubtitles-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f1c23a1f4ddec0c2b1ff34de8d1505b0eb9e2868d8edbcc1b6de13d02f32036 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_opensubtitles-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f1c23a1f4ddec0c2b1ff34de8d1505b0eb9e2868d8edbcc1b6de13d02f32036 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_openwebtext2-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5d6c19665f429ab1ccbe027da67f42bdaf219f819ab093673976eee55e015ff4 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_openwebtext2-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5d6c19665f429ab1ccbe027da67f42bdaf219f819ab093673976eee55e015ff4 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_philpapers-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 339ba5d8c044c4a3ff9b9a8eaa24da1d6c01b72972074eb671a7da049eeb7047 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_philpapers-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 339ba5d8c044c4a3ff9b9a8eaa24da1d6c01b72972074eb671a7da049eeb7047 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_pile-cc-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 731fdef4a43949b179ba0c540148ebc2fa41583dd583ef580dd812076c66a451 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_pile-cc-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 731fdef4a43949b179ba0c540148ebc2fa41583dd583ef580dd812076c66a451 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 66436569a43163afb2caf422d32c5f329899e74c49865d4d13881fd465fd9976 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 66436569a43163afb2caf422d32c5f329899e74c49865d4d13881fd465fd9976 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_pubmed-central-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 40b39d120d99a145690444e86acc3e3e24d41e6e0538a75e26929ad84926e5e0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_pubmed-central-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 40b39d120d99a145690444e86acc3e3e24d41e6e0538a75e26929ad84926e5e0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_stackexchange-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e524bfb3e21cbdaddc117403a50df598520c7bf5b2c60ad8f2372cfa564e79be -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_stackexchange-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e524bfb3e21cbdaddc117403a50df598520c7bf5b2c60ad8f2372cfa564e79be -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4eb69e314f0864ec8890e2323d7e76f8a8309692c4f090e2b41bf4be681a811d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4eb69e314f0864ec8890e2323d7e76f8a8309692c4f090e2b41bf4be681a811d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_uspto-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 789b2bdb31564d512b70f801316f49320a26c83ba361226bac0afb255341d477 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_uspto-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 789b2bdb31564d512b70f801316f49320a26c83ba361226bac0afb255341d477 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_wikipedia-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ef9ec0dd408316ca6537228a6812e839f14b30608973081d41efc47c138338da -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_wikipedia-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ef9ec0dd408316ca6537228a6812e839f14b30608973081d41efc47c138338da -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/piqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6048a3a2bb3ad1e6a3d98139618e06b4d7de766edd685bd38837596199c3f69f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/prost-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7c475f5b36a8b79f94c2be035441e7fd59dac021b0713b1fc72d256424c70b0b -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pubmedqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7a04a1fb1d2b19db84fd15c224015d6c0306a41195a4e71fe6abd48fb4d53b9f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/pubmedqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pubmedqa": {"acc": 0.324, "acc_stderr": 0.01480686473373886}}, "versions": {"pubmedqa": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/qa4mre_2011-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0d09f17c65768e797633494d2d218e4e46a26f718cab8b0bf3d156b073a8c437 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/qa4mre_2012-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7e17261820acb365966cb9431d93aec983b14393eaeefbc96e30a11cf58bc6df -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/qa4mre_2013-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 52fc431e94c67f983e28ebc70cf45e6c14116b0ae77dc1bf22347c705a65d054 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/qnli-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4281d4ff5cf1244358b0ea0220c67863c69fbade850696b43e8ff05138e01e12 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/qnli-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"qnli": {"acc": 0.5108914515833791, "acc_stderr": 0.00676380528502966}}, "versions": {"qnli": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/qqp-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 97b551b0fc3d239aad4929a2e8e79c986891aefd9fcd19441fea0382d507889e -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/race-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bdfdfab7fa1c7af0c1e161785e347b1b8071a15cbf971f6f2a9ae8c8e845199f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/race-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"race": {"acc": 0.23253588516746412, "acc_stderr": 0.013074460615265295}}, "versions": {"race": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/random_insertion-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 6c48baa6924f3635120f33062251c4b571b3d4e9fe46b14d91f54ddd1c857997 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/random_insertion-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"random_insertion": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"random_insertion": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/record-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a3e378fbde4e28f375cac1561bbfc7d7673c2af193628a774ad012d5192393aa -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/reversed_words-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 1d79fc4f0177f9624a487b9973f4e0e1d3f8404993b419a7b807a690ebbbb290 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/reversed_words-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"reversed_words": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"reversed_words": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/rte-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c80ce13c8c736087f1557f8736d5d318b540ff01e4bb7f55e568890dc8b0393e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/rte-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"rte": {"acc": 0.5379061371841155, "acc_stderr": 0.030009848912529117}}, "versions": {"rte": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/sciq-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 71cbb6e2a7ac4512c3761ea801d420eb3fac49d158c7e4deaa3ab8727bea923c -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/squad2-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b261e8885c11750ce6911bb11e8693de03d53758297c26fb14cfc1ef508862cb -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/squad2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 287e87cc6878debcc80d9b6df4e2d0a74ed29068e0e0a80906c8441843a17cee -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/squad2-v1-greedy_until: -------------------------------------------------------------------------------- 1 | e17e3d85c1d5adaf2d6b4b752c4babc2e0b3a6e144e6de70cb3b2287e85109b8 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/squad2-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | f5da6173402b274dc89130755c222c6ca6b2a3bacaaa4e4ab07be9322b7bad65 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/sst-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d2ebe3a63517d1d481aa1513bebe124c57a0904554a1e95f566979cfe67b1a7f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/sst-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"sst": {"acc": 0.5172018348623854, "acc_stderr": 0.016931824425903734}}, "versions": {"sst": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/swag-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | be4fcbad876124c4ba3c71970538a97fec0e36a9cc677c70b6c9243a7bcee0ec -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/toxigen-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7fedd930bafa92b9cca615a93ba92a4413244d2b77cf3f421a186815d721e0fa -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/triviaqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f8ec05b306b9f6187c0f8117cae441fb85a7a2e4670f4f9a1a3b632b1978421a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/triviaqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"triviaqa": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"triviaqa": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/triviaqa-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | f8ec05b306b9f6187c0f8117cae441fb85a7a2e4670f4f9a1a3b632b1978421a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/triviaqa-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"triviaqa": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"triviaqa": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/truthfulqa_gen-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 0d7c56e1aa71ffd8f94bde28f6e8dfdd35f7aaadffa0620bd2a27704253d6c14 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/truthfulqa_gen-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 1a280973bbac2b7ac29dd64dddac474fb4749585f7de893483b4034814466c67 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/truthfulqa_mc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 226a6783976177dc9ceda5688623ff37023242eff30ddf270b886bf7b9b32228 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/truthfulqa_mc-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 1e07020e9cf41d46ed65312eb39d2b8e6599673d4f0d6b67c0d0eba0efb493bb -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/webqs-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 96b218173468cc94552a0b946193bda89faba51f1bfc3e7945531f9dff8d6fe9 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/webqs-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"webqs": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"webqs": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 403a08da05e4c44d7e3dd3358382a7ba489c41d223e24cd1a9ed82ef1a2d004b -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wic-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wic": {"acc": 0.49216300940438873, "acc_stderr": 0.01980828765781383}}, "versions": {"wic": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wikitext-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | b6f83e6cf7535ee41b0057c3e2ec2cf7f2fa5a9119b305c479a83091d1142b2c -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wikitext-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | b6f83e6cf7535ee41b0057c3e2ec2cf7f2fa5a9119b305c479a83091d1142b2c -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/winogrande-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 90a3eff49de9173964d46f5ed57bcf9a78a72dd1bfe0e5323b25cebb40b49ea9 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/winogrande-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"winogrande": {"acc": 0.516179952644041, "acc_stderr": 0.014045126130978606}}, "versions": {"winogrande": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt14-en-fr-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 368ae7eec0f902b5123f2d5197caa5109a23942011c53fe68d9eaeee20180e46 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt14-fr-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | c1d9f7283755fbdd7ecd6cc4278b0ac25a80ac256b7071ea5f839ccd038e5974 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt16-de-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d30e23e38d9a45b9c31e1dfd14b58d0b7020df4b9c8a1c697aa6bc5fba8ce08a -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt16-en-de-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d71e2074af3770e9b29ac561caf2e1c29ad6b0dc50ec2e7bcc5501747b11f0da -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt16-en-ro-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 4be7fdda313394f19b5995b00ada1dfa3bb158ee1f020ef8d07ecea260fa60b2 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt16-ro-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d1b7c50751b0d5d7470b7f49f2bab9d09792c91460fc92cc34f06617013d7c65 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-cs-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | bfead9efdb1b2402a414c55929c8d8f956585f938a35466931d44e81d89cfe00 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-de-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d13b5a6915ca86ac6c6ebc50d9be0d0be3dfca600c12e896df53190d875de74d -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-de-fr-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 7f197bc281d6dbf9425900ef0dee7175021c43e355050f149f43b161c52bf0b0 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-cs-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 5a34e6863bf6965afd31653de50bac5fecf58db65dbaba46921504a2b7463786 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-de-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b6e9c305766ea23ce1027309f83c6d4c2ce8948d70b63a7858586ca34050d7fb -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-iu-v0-greedy_until: -------------------------------------------------------------------------------- 1 | f5688199890a48f73f2cc04a2152e35190f0e0ddd40e629fa24ee39d423ea389 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-ja-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 7fe61f5847a51e93e97c84b39f4420978727754e4b6cf636a27851c615857530 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-ja-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 7fe61f5847a51e93e97c84b39f4420978727754e4b6cf636a27851c615857530 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-km-v0-greedy_until: -------------------------------------------------------------------------------- 1 | eb5365c46f22ffec9a157991627d6e1fd1117fccffaedfc73619e93bafb5a408 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-pl-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 952f02575d4936d93c4d2808d86c4bf5f1f3a0901212acee6cbc1f9cbd30d39e -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-ps-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 8411c2cb73114cbd0c6e0f17eab2625d486cc3a601105deb0ea1338a401df689 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-ru-v0-greedy_until: -------------------------------------------------------------------------------- 1 | a1613831f69c1679a54670092af40ce76617b79d7cc837984803b0fc52bb8bde -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-ta-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 5fc556fa90bca7f1b1396e97e392eac8080b0ad53488358799b8fc0b21a94cb1 -------------------------------------------------------------------------------- /lm-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}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-zh-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 67f0333ddbcb07d7a9ac12919129a18fe4fea24e4826a11bbdde4fd5ed5ed83f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-en-zh-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 67f0333ddbcb07d7a9ac12919129a18fe4fea24e4826a11bbdde4fd5ed5ed83f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-fr-de-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 8a4b65c59dcac6591d46261909ee92ebcf41c19ee7442b12842302b2d8aeb36f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-iu-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 97bf664a8efa54b5366b8341f77b418106dd0cb26169d5b2d0144e4d3d2bc5c9 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-ja-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 1fd846f3c0104e794eb380dae7f648592092ab8bf59234c26d0a671bbbc28df1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-km-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | fb4ec81bb89c70df7e21b43e0e882915b7b71a2a85bb8d4b59e0c7938baaa4c2 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-pl-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 89274499d84176b1ffe4eaec06f2c89ca807342384dc946c2e348d00116aaade -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-ps-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | c3976465e3709b4bc371175cc1494c69fe096ea4ba7d114da779d2baa0a47466 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-ru-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 1477ab6542c26bd0222cc1aded174f33bf8d04d1cf6a1c0959aeca4ff3779adc -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-ta-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 111ea3efdc08f1cf536631b9426c3a20e482c575d009d2a8c71f59c027578eec -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wmt20-zh-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 07dbadfd6f2b2b9462ab6187dbfaabae6e5192ab89a8e4ede9237834b9364dd1 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wnli-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2ffd304d6096416eb29607e2e7642b1d6043163624967bcf4c4fc00fddc6c721 -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wnli-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wnli": {"acc": 0.3380281690140845, "acc_stderr": 0.05653887739133514}}, "versions": {"wnli": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wnli-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 8a0f81661d2ab2334bbc8031fac31c0c8882f1d9271dd51599d21dfdbb726dea -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wnli-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wnli": {"acc": 0.5633802816901409, "acc_stderr": 0.0592793555841297}}, "versions": {"wnli": 1}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wsc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 45865468eff5ca31e6a050947a6b3310d9d5ed19d0f2e578a32ecaf1c768600f -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wsc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wsc": {"acc": 0.5480769230769231, "acc_stderr": 0.049038186969314335}}, "versions": {"wsc": 0}} -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wsc273-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 26450d414c4581feb51a09882080e7a9b95882e7eab47b1751a4a6024b5a60ee -------------------------------------------------------------------------------- /lm-evaluation-harness/tests/testdata/wsc273-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wsc273": {"acc": 0.5164835164835165, "acc_stderr": 0.0303004740355766}}, "versions": {"wsc273": 0}} --------------------------------------------------------------------------------