Spaces:
Build error
Build error
| comment,do_eval,skip_train,dataset_subset_template,nontrivial_choices_given,nontrivial_choices_hidden,trivial_choices_given,trivial_choices_hidden,generative_non_true_task,generative_non_true_implausible,generative_true_task,negated_answers,counting,non_true_task_other,awkward_phrasing,ungrammatical,template_bug,long_distance,no_sep_2_sentences,verbose,answer_span_indices,non_natural_language | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_1,,,,,,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_10,,,,,,,,,,,,,,,,,True,True | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_2,,,,,,,,,,,,,,True,,,, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_3,,,,,,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_4,,,,,True,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_5,,,,,True,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_6,,,,,,,,,,,,,,,,True,, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_7,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_8,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_dbert_adversarial_qa_dbert_9,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_1,,,,,,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_10,,,,,,,,,,,,,,,,,True,True | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_2,,,,,,,,,,,,,,True,,,, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_3,,,,,,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_4,,,,,True,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_5,,,,,True,,,,,,,,,,,,, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_6,,,,,,,,,,,,,,,,True,, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_7,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_8,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_dbidaf_adversarial_qa_dbidaf_9,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_1,,,,,,,,,,,,,,,,,, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_10,,,,,,,,,,,,,,,,,True,True | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_2,,,,,,,,,,,,,,True,,,, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_3,,,,,,,,,,,,,,,,,, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_4,,,,,True,,,,,,,,,,,,, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_5,,,,,True,,,,,,,,,,,,, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_6,,,,,,,,,,,,,,,,True,, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_7,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_8,,,,,,,,,,,,,,,,,True, | |
| ,,,adversarial_qa_droberta_adversarial_qa_droberta_9,,,,,,,,,,,,,,,,,True, | |
| ,,,ag_news_classify,,True,,,,,,,,,,,,,,,, | |
| ,,,ag_news_classify_with_choices,True,,,,,,,,,,,,,,,,, | |
| ,,,ag_news_recommend,True,,,,,,,,,,,,,,,,, | |
| ,,,ag_news_which_section,,True,,,,,,,,,,,,,,,, | |
| ,,,ag_news_which_section_choices,True,,,,,,,,,,,,,,,,, | |
| ,,,amazon_polarity_Template_1,,,True,,,,,,,,,,,,,,, | |
| ,,,amazon_polarity_Template_2,,,,True,,,,,,,,,,True,,,, | |
| ,,,amazon_polarity_Template_3,,,,True,,,,,,,,,,,,,, | |
| ,,,amazon_polarity_Template_4,,,,True,,,,,,,,,,True,,,, | |
| ,,,amazon_polarity_Template_5,,,True,,,,,,,,,,,,,,, | |
| ,,,amazon_polarity_Template_6,,,True,,,,,,,,,,,True,,,, | |
| ,True,True,anli_GPT_3_style_r1,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_based_on_the_previous_passage_r1,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_does_S1_contradict_S2__r1,,,,,,,,True,,True,,,,,,,, | |
| ,True,True,anli_does_S1_entail_S2__r1,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_given_does_it_follow_that__r1,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_given_it_must_be_true_that__r1,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_GPT_3_style_r2,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_based_on_the_previous_passage_r2,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_does_S1_contradict_S2__r2,,,,,,,,True,,True,,,,,,,, | |
| ,True,True,anli_does_S1_entail_S2__r2,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_given_does_it_follow_that__r2,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_given_it_must_be_true_that__r2,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_GPT_3_style_r3,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_based_on_the_previous_passage_r3,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_does_S1_contradict_S2__r3,,,,,,,,True,,True,,,,,,,, | |
| ,True,True,anli_does_S1_entail_S2__r3,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_given_does_it_follow_that__r3,True,,,,,,,,,,,,,,,,, | |
| ,True,True,anli_given_it_must_be_true_that__r3,True,,,,,,,,,,,,,,,,, | |
| ,,,app_reviews_categorize_rating_using_review,,True,,,,,,,,,,,,,,,, | |
| ,,,app_reviews_convert_to_rating,True,,,,,,,,,,,,,,,,, | |
| ,,,app_reviews_convert_to_star_rating,,,,,,,,,,True,,,,,,,, | |
| ,,,app_reviews_generate_review,,,,,True,True,,,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Challenge_answer_qn,,,,,True,True,,,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Challenge_false,,,,,,,,True,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Challenge_qa_options,True,,,,,,,,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Challenge_test,True,,,,,,,,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Easy_answer_qn,,,,,True,True,,,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Easy_false,,,,,,,,True,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Easy_qa_options,True,,,,,,,,,,,,,,,,, | |
| ,,,ai2_arc_ARC_Easy_test,True,,,,,,,,,,,,,,,,, | |
| ,True,,circa_goldstandard1_judgement,True,,,,,,,,,,True,,,,,,, | |
| ,True,,circa_goldstandard2_judgement,True,,,,,,,,,,True,,,,,,, | |
| ,,,circa_judgement,,True,,,,,,,,True,True,,,,,,, | |
| ,,,circa_possible_qn,,,,,True,,,,,,,,,,,,, | |
| ,,,circa_question_declarative,,,,,,,,,,True,,,,,,,, | |
| ,,,cnn_dailymail_3.0.0_generate_story,,,,,True,,,,,,,,,,,,, | |
| ,,,cnn_dailymail_3.0.0_news_card_view,,,,,,,True,,,,,,,True,,,, | |
| ,,,cnn_dailymail_3.0.0_news_stock,,,,,,,True,,,,,,,True,,,, | |
| ,,,cnn_dailymail_3.0.0_news_summary,,,,,,,True,,,,,,,True,,True,, | |
| ,,,cnn_dailymail_3.0.0_spice_up_story,,,,,True,,,,,,,,,,,,, | |
| ,,,codah_codah_answer_no_option,,True,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_answer_with_option,True,,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_answer_with_option_idx,True,,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_answer_with_option_post,True,,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_choose_from_list,True,,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_finish_from_the_list,True,,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_finish_from_the_list_post,True,,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_finish_pre,,True,,,,,,,,,,,,,,,, | |
| ,,,codah_codah_question_category,,,,,,,,,,True,,,,,,,, | |
| ,,,codah_codah_question_category_bis,,,,,,,,,,True,,,,,,,, | |
| ,,,common_gen_Example_prompt,,,,,,,True,,,,,,,,,,, | |
| ,,,common_gen_Given_concepts,,,,,,,True,,,,,,,,,,, | |
| ,,,common_gen_Put_together,,,,,,,True,,,,,,,,,,, | |
| ,,,common_gen_choice_in_concept_centric_sentence_generation,,,,,,,True,,,,,,,,,,, | |
| ,,,common_gen_sentence_to_concepts,,,,,,,,,,True,,,,,,,, | |
| ,,,cos_e_v1.11_description_question_option_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cos_e_v1.11_description_question_option_text,True,,,,,,,,,,,,,,,,, | |
| ,,,cos_e_v1.11_generate_explanation_given_text,True,,,,,,True,,,,,,True,,,,, | |
| ,,,cos_e_v1.11_generate_explanation_no_given_answer,,True,,,,,True,,,,,,,,,,, | |
| ,,,cos_e_v1.11_question_description_option_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cos_e_v1.11_question_description_option_text,True,,,,,,,,,,,,,,,,, | |
| ,,,cos_e_v1.11_question_option_description_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cos_e_v1.11_question_option_description_text,True,,,,,,,,,,,,,,,,, | |
| revisit,,,cosmos_qa_context_description_question_answer_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_context_description_question_answer_text,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_context_description_question_text,,True,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_context_question_answer_description_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_context_question_answer_description_text,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_context_question_description_answer_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_context_question_description_answer_text,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_context_question_description_text,,True,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_description_context_question_answer_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_description_context_question_answer_text,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_description_context_question_text,,True,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_no_prompt_id,True,,,,,,,,,,,,,,,,, | |
| ,,,cosmos_qa_no_prompt_text,True,,,,,,,,,,,,,,,,, | |
| ,,,dbpedia_14_dbpedia_1,,True,,,,,,,,,,,,,,,, | |
| ,,,dbpedia_14_dbpedia_10,True,,,,,,,,,,,,,,,,, | |
| ,,,dbpedia_14_dbpedia_3,,True,,,,,,,,,,,,,,,, | |
| ,,,dbpedia_14_dbpedia_5,,True,,,,,,,,,,,,,,,, | |
| ,,,dbpedia_14_dbpedia_7,,True,,,,,,,,,,,,,,,, | |
| ,,,dbpedia_14_dbpedia_8,,True,,,,,,,,,,,,,,,, | |
| ,,,dbpedia_14_dbpedia_9,True,,,,,,,,,,,,,,,,, | |
| ,,,dream_answer_to_dialogue,,,,,True,,,,,,,,,,,,, | |
| ,,,dream_baseline,True,,,,,,,,,,,,,,,,, | |
| ,,,dream_conversation,True,,,,,,,,,,,,,,,,, | |
| ,,,dream_generate_first_utterance,,,,,True,,,,,,,,,,,,, | |
| ,,,dream_generate_last_utterance,,,,,True,,,,,,,,,,,,, | |
| ,True,,emo_feeling,True,,,,,,,,,,,,,,,,, | |
| ,True,,emo_final_message,True,,,,,,,,,,,,,,,,, | |
| ,True,,emo_persons_describe,True,,,,,,,,,,,,,,,True,, | |
| ,True,,emo_persons_infer,True,,,,,,,,,,,,,,,,, | |
| ,True,,emo_spoke_last,True,,,,,,,,,,,,,,,,, | |
| ,,,freebase_qa_inference_chain_prompt,,,,,,,,,,True,,,,,,,, | |
| ,,,freebase_qa_inference_chain_prompt_context,,,,,,,,,,True,,,,,,,, | |
| ,,,freebase_qa_qa_context_1,,,,,,,,,,,,,,,,,, | |
| ,,,freebase_qa_qa_context_2,,,,,,,,,,,,,,,,,, | |
| ,,,freebase_qa_qa_template_basic,,,,,,,,,,,,,,,,,, | |
| ,,,gigaword_Document_,,,,,,,True,,,,,,,,,,, | |
| ,,,gigaword_Summarize_this_document_,,,,,,,True,,,,,,,,,,, | |
| ,,,gigaword_TLDR,,,,,,,True,,,,,,,,,,, | |
| ,,,gigaword_generate_summary_for_this,,,,,,,True,,,,,,,,,,, | |
| ,,,gigaword_in_a_nutshell,,,,,,,True,,,,,,,,,,, | |
| ,,,gigaword_reverse_writing,,,,,,,,,,True,,,,,,,, | |
| ,,,gigaword_reverse_writing_2,,,,,,,True,,,,,,,,,,, | |
| ,,,gigaword_summarize_,,,,,,,True,,,,,,,,,,, | |
| ,,,gigaword_write_one_sentence,,,,,,,True,,,,,,,,,,, | |
| ,True,True,glue_cola_Following_sentence_acceptable,True,,,,,,,,,,,,,,,,, | |
| ,True,True,glue_cola_Make_sense_yes_no,,,True,,,,,,,,,,,,,,, | |
| ,True,True,glue_cola_Previous_sentence_acceptable,,,,True,,,,,,,,,,,,,, | |
| ,True,True,glue_cola_editing,,,True,,,,,,,,,,,,,,, | |
| ,True,True,glue_cola_jinja_example,,,,True,,,,,,,,,,,,,, | |
| ,True,,glue_mrpc_equivalent,True,,,,,,,,,,,,,,True,,, | |
| ,True,,glue_mrpc_paraphrase,,,,True,,,,,,,,,,,,,, | |
| ,True,,glue_mrpc_replace,,,,True,,,,,,,,,,,,,, | |
| ,True,,glue_mrpc_same_thing,,,,True,,,,,,,,,,,True,,, | |
| ,True,,glue_mrpc_want_to_know,,,,True,,,,,,,,,,,True,,, | |
| ,,,glue_qqp_answer,,,,True,,,,,,,,,,,,,, | |
| ,,,glue_qqp_duplicate,,,,True,,,,,,,,,,,,,, | |
| ,,,glue_qqp_duplicate_or_not,True,,,,,,,,,,,,,,,,, | |
| ,,,glue_qqp_quora,,,,True,,,,,,,,,,,,True,, | |
| ,,,glue_qqp_same_thing,,,,True,,,,,,,,,,,,,, | |
| ,,,glue_sst2_following_positive_negative,True,,,,,,,,,,,,,,,,, | |
| ,,,glue_sst2_happy_or_mad,True,,,,,,,,,,,,,,,,, | |
| ,,,glue_sst2_positive_negative_after,True,,,,,,,,,,,,,,,,, | |
| ,,,glue_sst2_review,True,,,,,,,,,,,,,,,,, | |
| ,,,glue_sst2_said,True,,,,,,,,,,,,,,,,, | |
| ,,True,glue_stsb_examples,,,,,,,,,,,,,,,,,, | |
| ,,True,glue_stsb_rank,,,,,,,,,,,,,,,,,, | |
| ,,True,glue_stsb_rate,,,,,,,,,,,,,,,,,, | |
| ,,True,glue_stsb_score,,,,,,,,,,,,,,,,,, | |
| ,,True,glue_stsb_similarity,,,,,,,,,,,,,,,,,, | |
| ,True,True,hans_GPT_3_style,True,,,,,,,,,,,,,,,,, | |
| ,True,True,hans_Suppose_Can_we_infer_that_,,,,True,,,,,,,,,,,,,, | |
| ,True,True,hans_based_on_the_previous_passage,,,,True,,,,,,,,,,,,,, | |
| ,True,True,hans_does_S1_entail_S2_,,,True,,,,,,,,,,,,,,, | |
| ,True,True,hans_given_does_it_follow_that_,,,True,,,,,,,,,,,,,,, | |
| ,True,True,hans__does_the_previous_passage_support_the_claim_that,,,,True,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_0,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_1,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_2,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_3,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_reversed_0,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_reversed_1,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_reversed_2,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_YesNo_reversed_3,,,True,,,,,,,,,,,,,,, | |
| ,,,hellaswag_complete_first_then,True,,,,,,,,,,,,,,,,, | |
| ,,,hellaswag_first_then,True,,,,,,,,,,,,,,,,, | |
| ,,,hellaswag_how_ends,True,,,,,,,,,,,,,,,,, | |
| ,,,hellaswag_if_begins_how_continues,True,,,,,,,,,,,,,,,,, | |
| ,,,hellaswag_which_ending,True,,,,,,,,,,,,,,,,, | |
| ,,,imdb_imdb_1,,True,,,,,,,,,,,,,,,, | |
| ,,,imdb_imdb_2,,True,,,,,,True,,,,,,,,,, | |
| ,,,imdb_imdb_3,,True,,,,,,,,,,,,,,,, | |
| ,,,imdb_imdb_4,,True,,,,,,,,,,,,,,,, | |
| ,,,imdb_imdb_5,,True,,,,,,,,,,,,True,,,, | |
| ,,,imdb_imdb_6,,True,,,,,,,,,,,,,,,, | |
| ,,,imdb_imdb_7,,True,,,,,,,,,,,,,,,, | |
| ,,,imdb_imdb_8,,True,,,,,,,,,,,,,,,, | |
| ,,,imdb_imdb_9,,,,True,,,,,,,,,,,,,, | |
| ,True,,mc_taco_mc_taco_1,,,,True,,,,,,,,,,,,,, | |
| ,,,mc_taco_mc_taco_2,,,,,,,,,,True,,,,,,,, | |
| ,True,,mc_taco_mc_taco_3,,,True,,,,,,,,,,,True,,,, | |
| ,,,mc_taco_mc_taco_4,True,,,,,,,,,True,,,,,,,, | |
| ,,,mc_taco_mc_taco_5,,,,,True,,,,,,,,,,,,, | |
| ,,,mc_taco_mc_taco_6,,True,,,,,,,,,,,,,,,, | |
| ,True,True,nq_open_context_self_description,,,,,,,,,,,,,,,,,, | |
| ,,True,nq_open_guess_question,,,,,True,,,,,,,,,,,,, | |
| ,True,True,nq_open_question_answer,,,,,,,,,,,,,,,,,, | |
| ,True,True,nq_open_question_with_instruction,,,,,,,,,,,,,,,,,, | |
| ,,,onestop_english_ara_context,True,,,,,,,,,,,,,,,,, | |
| ,,,onestop_english_assess,True,,,,,,,,,,,,,True,,,, | |
| ,,,onestop_english_ats,True,,,,,,,,,,,,,,,,, | |
| ,,,onestop_english_esl_context,True,,,,,,,,,,,,,True,,,, | |
| ,,,onestop_english_esl_variation,True,,,,,,,,,,,,,True,,,, | |
| ,True,,openbookqa_main_choices,True,,,,,,,,,,,,,,,,, | |
| ,True,,openbookqa_main_choose_an_answer_with_options,True,,,,,,,,,,,,,,,,, | |
| ,True,,openbookqa_main_only_options,True,,,,,,,,,,,,,,,,, | |
| ,True,,openbookqa_main_pick_answer_with_options,True,,,,,,,,,,,,,,,,, | |
| ,True,,openbookqa_main_pick_using_id,True,,,,,,,,,,,,,,,,, | |
| ,True,,openbookqa_main_which_correct,True,,,,,,,,,,,,,,,,, | |
| ,,True,openbookqa_main_which_correct_inverse,True,,,,,,,,,,,,True,,,,, | |
| ,,,paws_labeled_final_Concatenation,,,True,,,,,,,,,,True,,,,, | |
| ,,,paws_labeled_final_Concatenation_no_label,,,,True,,,,,,,,,True,,,,, | |
| ,,,paws_labeled_final_Meaning,,,True,,,,,,,,,,True,,,,, | |
| ,,,paws_labeled_final_Meaning_no_label,,,,True,,,,,,,,,True,,,,, | |
| ,,,paws_labeled_final_PAWS_ANLI_GPT3,True,,,,,,,,,True,,,,,,,, | |
| ,,,paws_labeled_final_PAWS_ANLI_GPT3_no_label,,True,,,,,,,,True,,,,,,,, | |
| ,,,piqa_Correct_the_solution,,,,,True,,,,,,,,,,,,, | |
| ,,,piqa_Correct_the_solution_if_false_from_sol_1,,,,,True,,,,,,,,,,,,, | |
| ,,,piqa_Correct_the_solution_if_false_from_sol_2,,,,,True,,,,,,,,,,,,, | |
| should use jinja choice,,,piqa_Does_this_solution_make_sense_sol1,,,,True,,,,,,,,,,,,,, | |
| ,,,piqa_Does_this_solution_make_sense_sol2,,,,True,,,,,,,,,,,,,, | |
| ,,,piqa_Generate_a_similar_but_wrong_solution,,,,,True,,,,,,,,,,,,, | |
| ,,,piqa_choose_the_most_appropriate_solution,True,,,,,,,,,,,,,,,,, | |
| duplicate of above,,True,piqa_choose_the_most_appropriate_solution_reorder_solution,True,,,,,,,,,,,,,,,,, | |
| ,,,piqa_no_prompt_needed,,,,,True,,,,,,,,,,,,, | |
| ,,,qa_srl_aq,,,,,True,True,,,,,,,,,,,, | |
| ,,,qa_srl_context_answer,,,,,True,,,,,,,,,,,,, | |
| ,,,qa_srl_context_qn,,,,,True,,,,,,,,,,,,, | |
| ,,,qa_srl_predicate,,,,,,,,,,True,,,,,,,, | |
| need non-naive metric,True,,qa_srl_qa,,,,,,,,,,,,,,,,,, | |
| ,,,qasc_is_correct_0,,,,True,,,,,,,,,,,,,, | |
| ,,,qasc_is_correct_1,,,,True,,,,,,,,,,,,,, | |
| ,,,qasc_qu_combined,True,,,,,,,,,,,,,,,,, | |
| ,,,qasc_sep_combined_can_tell,True,,,,,,,,,,,,,,,,, | |
| ,,,qasc_sep_qu,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_context_description_question_answer_id,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_context_description_question_answer_text,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_context_description_question_text,,True,,,,,,,,,,,,,,,, | |
| ,,,quail_context_question_answer_description_id,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_context_question_answer_description_text,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_context_question_description_answer_id,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_context_question_description_answer_text,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_context_question_description_text,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_description_context_question_answer_id,,True,,,,,,,,,,,,,,,, | |
| ,,,quail_description_context_question_answer_text,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_description_context_question_text,,True,,,,,,,,,,,,,,,, | |
| ,,,quail_no_prompt_id,True,,,,,,,,,,,,,,,,, | |
| ,,,quail_no_prompt_text,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_para_question_1,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,quartz_para_question_1_reverse,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_para_question_2,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_para_question_3_choices,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_para_question_4_choices,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_para_question_plain,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,quartz_para_question_plain_reverse,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_question_para_1,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,quartz_question_para_1_reverse,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_question_para_2,True,,,,,,,,,,,,,,,,, | |
| ,,,quartz_question_para_3,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,quartz_question_para_3_reverse,True,,,,,,,,,,,,,,,,, | |
| ,,,quoref_Template_1,,,,,,,,,,,,,,,,,, | |
| ,,,quoref_Template_2,,,,,,,,,,,,,,True,,,, | |
| ,,,quoref_Template_3,,,,,True,,,,,,True,,,,,,, | |
| ,,,quoref_Template_4,,,,,,,,,,True,,,,,,,True, | |
| ,,,quoref_Template_5,,,,,,,,,,True,,,,,,,, | |
| ,,,race_high_Read_the_article_and_answer_the_question_no_option_,,True,,,,,,,,,,,,,,,, | |
| ,True,,race_high_Read_the_article_and_select_the_best_answer,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,race_high_Read_the_article_and_select_the_best_answer2,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,race_high_Read_the_article_and_select_the_best_answer3,True,,,,,,,,,,,,,,,,, | |
| ,,,race_high_Write_a_multi_choice_question_for_the_following_article,,,,,True,,,,,,,,,,,,, | |
| ,,,race_high_Write_a_multi_choice_question_for_the_following_article_2,,,,,True,,,,,,,,,,,,, | |
| ,,,race_middle_Read_the_article_and_answer_the_question_no_option_,,True,,,,,,,,,,,,,,,, | |
| ,True,,race_middle_Read_the_article_and_select_the_best_answer,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,race_middle_Read_the_article_and_select_the_best_answer2,True,,,,,,,,,,,,,,,,, | |
| near duplicate of the above,,True,race_middle_Read_the_article_and_select_the_best_answer3,True,,,,,,,,,,,,,,,,, | |
| ,,,race_middle_Write_a_multi_choice_question_for_the_following_article,,,,,True,,,,,,,,,,,,, | |
| ,,,race_middle_Write_a_multi_choice_question_for_the_following_article_2,,,,,True,,,,,,,,,,,,, | |
| ,,,ropes_funky_prompt,True,,,,,,,,,,,,,,,,, | |
| ,,,ropes_plain,True,,,,,,,,,,,,,,,,, | |
| ,,,ropes_plain_bottom_hint,True,,,,,,,,,,,,,True,,,, | |
| ,,,ropes_plain_no_background,True,,,,,,,,,True,,,,,,,, | |
| ,,,ropes_prompt_beginning,True,,,,,,,,,,,,,,,,, | |
| ,,,ropes_prompt_bottom_hint_beginning,True,,,,,,,,,,,,,,,,, | |
| ,,,ropes_prompt_bottom_no_hint,True,,,,,,,,,True,,,,,,,, | |
| ,,,ropes_prompt_mix,True,,,,,,,,,,,,,True,,,, | |
| ,,,rotten_tomatoes_rt_1,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_10,True,,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_2,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_3,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_4,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_5,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_6,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_7,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_8,,True,,,,,,,,,,,,,,,, | |
| ,,,rotten_tomatoes_rt_9,,,,True,,,,,,,,,,,,,, | |
| ,,,sciq_Template_0,,True,,,,,,,,,,,True,,,,, | |
| ,,,sciq_Template_1,,True,,,,,,,,,,,True,,,,, | |
| ,True,,social_i_qa_social_i_qa1,True,,,,,,,,,,,,,,,,, | |
| ,,,social_i_qa_social_i_qa2,,True,,,,,,,,,,,,,,,, | |
| select answer by ordinal word,True,,social_i_qa_social_i_qa3,True,,,,,,,,,,,,,,,,, | |
| ,,,social_i_qa_social_i_qa4,,,,,True,,,,,,,,,,,,, | |
| 4-way to binary classification,,,social_i_qa_social_i_qa5,,,,True,,,,,,,,,,,,,, | |
| ,,,squad_v2_Jeopardy_with_Context,,,,,True,,,,,,,,,,,,, | |
| ,,,squad_v2_Jeopardy_without_Context,,,,,True,,,,,True,,,,,,,, | |
| ,,,squad_v2_Questions_with_Context,True,,,,,,,,,,,,,,,,, | |
| nicely randomnized prompt phrasing,,,squad_v2_Questions_with_Context_Without_Prompt_Keywords,True,,,,,,,,,,,,,,,,, | |
| ,,,squad_v2_Topic_Prediction_Context,,,,,,,,,,True,,,,,,,, | |
| ,,,squad_v2_Topic_Prediction_Context_with_randomized_prompt_options,,,,,,,,,,True,,,,,,,, | |
| ,,,squad_v2_Topic_Prediction_Context_with_randomized_prompt_options_placed_in_the_end,,,,,,,,,,True,,,,,,,, | |
| ,,,squad_v2_Topic_Prediction_Question_and_Answer_Pair,,,,,,,,,,True,,,,,,,, | |
| ,,,squad_v2_Trivia,,,,,,,,,,True,,,,,,,, | |
| ,True,,super_glue_boolq_GPT_3_Style,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_boolq_I_wonder_,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_boolq_based_on_the_following_passage,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_boolq_based_on_the_previous_passage,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_boolq_could_you_tell_me_,,,,True,,,,,,,,,,,,,, | |
| ,True,True,super_glue_cb_GPT_3_style,True,,,,,,,,,,,,,,,,, | |
| ,True,True,super_glue_cb_based_on_the_previous_passage,True,,,,,,,,,,,,,,,,, | |
| contrapositive,True,True,super_glue_cb_does_S1_contradict_S2_,True,,,,,,,,,True,,,,,,,, | |
| ,True,True,super_glue_cb_does_S1_entail_S2_,True,,,,,,,,,,,,,,,,, | |
| ,True,True,super_glue_cb_given_does_it_follow_that_,True,,,,,,,,,,,,,,,,, | |
| must/might/may be true,True,True,super_glue_cb_given_it_must_be_true_that_,True,,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_copa_C1_or_C2_premise_so_because_,True,,,,,,,,,,,,,,,,, | |
| effect examples,True,,super_glue_copa__As_a_result_C1_or_C2_,True,,,,,,,,,,,,,,,,, | |
| effect examples,True,,super_glue_copa__What_could_happen_next_C1_or_C2_,True,,,,,,,,,,,,,,,,, | |
| cause examples,True,,super_glue_copa__which_may_be_caused_by,True,,,,,,,,,,,,,,,,, | |
| effect examples,True,,super_glue_copa__which_may_cause_C1_or_C2_,True,,,,,,,,,,,,,,,,, | |
| cause examples,True,,super_glue_copa__why_C1_or_C2,True,,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_multirc_I_was_going_to_say_,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_multirc_Would_it_be_good_to_answer_,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_multirc_is_a_correct_answer_,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_multirc_is_the_correct_answer_,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_multirc_paragraph_question_is_it_,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_record_Can_you_figure_out_,,True,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_record_In_the_question_above_the_placeholder_stands_for,,True,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_record_What_could_the_placeholder_be_,True,,,,,,,,,,,,,,,,, | |
| no difference here?,True,,super_glue_record_Which_one_is_the_placeholder_,True,,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_record_the_placeholder_refers_to_,,True,,,,,,,,,,,,,,,, | |
| ,True,True,super_glue_rte_GPT_3_style,True,,,,,,,,,,,,,,,,, | |
| ,True,True,super_glue_rte_Suppose_Can_we_infer_that_,,,,True,,,,,,,,,,,,,, | |
| ,True,True,super_glue_rte_based_on_the_previous_passage,,,,True,,,,,,,,,,,,,, | |
| ,True,True,super_glue_rte_does_S1_entail_S2_,,,True,,,,,,,,,,,,,,, | |
| ,True,True,super_glue_rte_given_does_it_follow_that_,,,,True,,,,,,,,,,,,,, | |
| ,True,True,super_glue_rte__Therefore_we_re_licensed_to_say_that_,,,,True,,,,,,,,,,,,,, | |
| ,True,True,super_glue_rte__does_the_previous_passage_support_the_claim_that,,,,True,,,,,,,,,,,,,, | |
| ,True,,super_glue_wic_GPT_3_prompt,,,,True,,,,,,,,,,,True,,, | |
| ,True,,super_glue_wic_GPT_3_prompt_with_label,,,True,,,,,,,,,,,,True,,, | |
| ,True,,super_glue_wic_question_context,,,,True,,,,,,,,,,,True,,, | |
| ,True,,super_glue_wic_question_context_meaning,,,,True,,,,,,,,,,,True,,, | |
| ,True,,super_glue_wic_question_context_meaning_with_label,,,True,,,,,,,,,,,,True,,, | |
| ,True,,super_glue_wic_similar_sense,,,,True,,,,,,,,,,,True,,, | |
| ,True,,super_glue_wsc.fixed_Here_p_stands_for_,,,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_wsc.fixed_In_the_previous_sentence_the_pronoun_refers_to_,,,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_wsc.fixed_Who_is_are_,,,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_wsc.fixed_in_the_passage_above_the_pronoun_X_refers_to_,,,,,,,,,,,,,,,,,, | |
| ,True,,super_glue_wsc.fixed_passage_what_does_the_pronoun_refer_to_,,,,,,,,,,,,,,,,,, | |
| cast 4-way classification as binary,,,swag_regular_YesNo_0,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_YesNo_1,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_YesNo_2,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_YesNo_3,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_YesNo_reversed_0,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_YesNo_reversed_1,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_YesNo_reversed_2,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_YesNo_reversed_3,,,True,,,,,,,,,,,,,,, | |
| ,,,swag_regular_complete_first_then,True,,,,,,,,,,,,,,,,, | |
| ,,,swag_regular_first_then,True,,,,,,,,,,,,,,,,, | |
| ,,,swag_regular_how_ends,True,,,,,,,,,,,,,,,,, | |
| ,,,swag_regular_if_begins_how_continues,True,,,,,,,,,,,,,,,,, | |
| ,,,swag_regular_which_ending,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_ABBR,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_ABBR_context_first,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_DESC,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_DESC_context_first,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_ENTY,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_ENTY_context_first,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_HUM,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_HUM_context_first,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_LOC,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_LOC_context_first,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_NUM,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_NUM_context_first,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_open,,True,,,,,,,,,,,,,,,, | |
| ,,,trec_fine_grained_open_context_first,,True,,,,,,,,,,,,,,,, | |
| answers are not what the questions ask for,,True,trec_gao_et_al_1,,,,,,,,,,,,True,,,,,, | |
| answers are not what the questions ask for,,True,trec_gao_et_al_2,,,,,,,,,,,,True,,,,,, | |
| ,,,trec_trec1,True,,,,,,,,,,,,,,,,, | |
| ,,,trec_trec2,True,,,,,,,,,,,,,,,,, | |
| ,,,trivia_qa_rc_context_self_description,,,,,,,,,,,,,,,,,, | |
| ,,,trivia_qa_rc_guess_question,,,,,True,True,,,,True,,,,,,,, | |
| ,,,trivia_qa_rc_question_answer,,,,,,,,,,,,,,,,,, | |
| ,,,trivia_qa_rc_question_with_instruction,,,,,,,,,,,,,,,,,, | |
| ,,,trivia_qa_rc_reading_comprehension_1,,,,,,,,,,True,,,,,,,, | |
| ,,,trivia_qa_rc_reading_comprehension_2,,,,,,,,,,True,,,,,,,, | |
| ,,,web_questions_count_answers,,,,,,,,,True,,,,,,,,, | |
| ,,,web_questions_credible_question,,,,,True,,,,,,,,,,,,, | |
| ,,,web_questions_if_answers_what_question,,,,,True,,,,,,,,,,,,, | |
| ,,,web_questions_potential_correct_answer,,,,,,,,,,,True,,,,,,, | |
| ,,,web_questions_question_answer,,,,,,,,,,,,,,,,,, | |
| ,,,web_questions_suggest_question,,,,,True,,,,,,,,,,,,, | |
| ,,,wiki_bio_comprehension,,,,,,,,,,True,,,,,,,, | |
| ,,,wiki_bio_guess_person,,,,,,,,,,True,,,,,,,, | |
| ,,,wiki_bio_key_content,,,,,,,,,,True,,,,,,,, | |
| ,,,wiki_bio_what_content,,,,,,,,,,True,,,,,,,, | |
| "should rephrase ""summarize""",,,wiki_bio_who,,,,,,,,,,,,,,,,,, | |
| ,,,wiki_hop_original_Choose_Best_Object_Candidate,,,,,,,,,,True,,,,,,,,True | |
| ,,,wiki_hop_original_Explain_Relation,,True,,,,,,,,True,,,,,,,, | |
| ,,,wiki_hop_original_Generate_Fact_Triple,,,,,,,,,,True,,,,,,,,True | |
| ,,,wiki_hop_original_Generate_Object_Answer,,,,,,,,,,True,,,,,,,,True | |
| ,,,wiki_hop_original_Generate_Subject_Answer,,,,,,,,,,True,,,,,,,,True | |
| ,,,wiki_hop_original_Indirect_Question_about_Birthplace_Citizenship_Place_of_Death,,,,,,,,,,,,,True,,,,, | |
| ,,,wiqa_effect_with_label_answer,True,,,,,,,,,,,,,,,,, | |
| ,,,wiqa_effect_with_string_answer,True,,,,,,,,,,,,,,,,, | |
| ,,,wiqa_impacting_the_process,,,,True,,,,,,,,,,,,,, | |
| ,,,wiqa_question_type,,,,,,,,,,True,,,,,,,, | |
| ,,,wiqa_remove_first_step,,,,,,,,,,True,,,,,,,, | |
| ,,,wiqa_remove_first_step_bis,,,,,,,,,,True,,,,,,,, | |
| ,,,wiqa_remove_last_step,,,,,,,,,,True,,,,,,,, | |
| ,,,wiqa_remove_last_step_bis,,,,,,,,,,True,,,,,,,, | |
| ,True,,xsum_Document_,,,,,,,,,,,,,,,,,, | |
| ,True,,xsum_Summarize_this_document_,,,,,,,,,,,,,,,,,, | |
| ,True,,xsum_TLDR,,,,,,,,,,,,,,,,,, | |
| ,True,,xsum_generate_summary_for_this,,,,,,,,,,,,,,,,,, | |
| ,True,,xsum_summarize_,,,,,,,,,,,,,,True,,,, | |
| ,True,,xsum_write_one_sentence,,,,,,,,,,,,,,,,,, | |
| ,,,yelp_review_full_based_on_that,,True,,,,,,,,,,,,,,,, | |
| ,,,yelp_review_full_format_rating,,True,,,,,,,,,,,,,,,, | |
| ,,,yelp_review_full_format_score,,True,,,,,,,,,,,,,,,, | |
| ,,,yelp_review_full_format_star,,True,,,,,,,,,,,,,,,, | |
| ,,,yelp_review_full_on_a_scale,,True,,,,,,,,,,,,,,,, | |
| ,,,yelp_review_full_so_i_would,,True,,,,,,,,,,,,,,,, | |
| ,,,yelp_review_full_this_place,,True,,,,,,,,,,,,,,,, | |