diff --git "a/.gitattributes" "b/.gitattributes" --- "a/.gitattributes" +++ "b/.gitattributes" @@ -32,3 +32,2593 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/evaluation/generation/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b84boscar/evaluation/generation/examples.4b284b84boscar_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_this_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_guaranteed-true_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_summarize_above_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_tldr_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_Correct-the-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Generate-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_valid_binary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_DOC_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_yes_no_question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_what_is_the_correct_ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_does-underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Generate-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_very-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_yes_no_question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_Replace_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_article_summary_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_cause_effect_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Novel-Correct-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_yes_no_question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_guaranteed-true_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_article_summary_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_does-underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_guaranteed-true_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_Correct-the-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_coherent_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-Question-First_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_Replace_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_tldr_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_this_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_valid_binary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_choose-the-most-appropriate-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_does-underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Novel-Correct-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_yes_no_question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_no-prompt-needed_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_plausible_alternatives_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_article_summary_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_choose_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_should-assume_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_cause_effect_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_should-assume_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_yes_no_question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_no-prompt-needed_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_Correct-the-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_Replace_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_non-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_explicit-graph-description2_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_Replace_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_what_is_the_correct_ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_guaranteed-true_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_GPT-3-Style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_best_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_choose_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_tldr_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_DOC_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Novel-Correct-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_non-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_summarize_above_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_write_abstract_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Story-Continuation-and-Options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_tldr_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Novel-Correct-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-Question-First_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-Question-First_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_choose-the-most-appropriate-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_True-or-False_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_pick_correct_choice_index_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_coherent_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_non-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_pick_correct_choice_index_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_after_reading_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_very-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Story-Continuation-and-Options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_explicit-graph-description2_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_DOC_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_pick_correct_choice_index_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_guaranteed-true_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_yes_no_question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_rephrase_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_after_reading_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_pick_correct_choice_index_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Choose-Story-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_explicit-graph-description2_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_tldr_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_very-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_article_summary_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_choose-the-most-appropriate-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_Replace_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_does-underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_yes_no_question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_what_is_the_correct_ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_rephrase_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_pick_correct_choice_index_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_article_summary_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_GPT-3-Style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Choose-Story-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_this_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_very-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_Replace_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_valid_binary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_does-underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_plausible_alternatives_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_does-it-follow-that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_write_abstract_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_explicit-graph-description2_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_should-assume_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_valid_binary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_stand-for_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Choose-Story-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_summarize_above_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_coherent_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_does-it-follow-that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Novel-Correct-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_no-prompt-needed_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_explicit-graph-description2_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_choose_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_DOC_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_exercise_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_Correct-the-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_stand-for_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_best_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_non-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_stand-for_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_plausible_alternatives_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_non-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_article_summary_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_Correct-the-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_tldr_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_best_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Story-Continuation-and-Options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Story-Continuation-and-Options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Generate-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_non-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_does-it-follow-that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_stand-for_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_should-assume_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_plausible_alternatives_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_create_text_for_me_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_stand-for_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_what_is_the_correct_ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_Correct-the-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_explicit-graph-description2_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_GPT-3-Style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Novel-Correct-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Novel-Correct-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_very-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_choose_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_very-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_plausible_alternatives_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_guaranteed-true_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_guaranteed-true_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_choose-the-most-appropriate-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_no-prompt-needed_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_what_is_the_correct_ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Story-Continuation-and-Options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_non-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_exercise_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_True-or-False_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_article_summary_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_True-or-False_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_does-it-follow-that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_Correct-the-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_this_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Story-Continuation-and-Options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_does-it-follow-that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_best_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_explicit-graph-description2_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_does-underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_create_text_for_me_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_Replace_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_what_is_the_correct_ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_no-prompt-needed_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Choose-Story-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_create_text_for_me_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Story-Continuation-and-Options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_guaranteed-true_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_after_reading_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_guaranteed-true_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Answer-Given-options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Choose-Story-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_implicit-graph-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_guaranteed-true_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_very-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_rephrase_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_should-assume_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_implicit-graph-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_exercise_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_non-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_write_abstract_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_after_reading_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_DOC_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_does-underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_write_abstract_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_Correct-the-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_rephrase_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_non-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_does-it-follow-that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Answer-Given-options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_guaranteed-true_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_implicit-graph-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_Replace_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_create_text_for_me_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_GPT-3-Style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_no-prompt-needed_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Choose-Story-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Generate-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_stand-for_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_stand-for_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_pick_correct_choice_index_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_GPT-3-Style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_valid_binary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_pick_correct_choice_index_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_what_is_the_correct_ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Novel-Correct-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_guaranteed-true_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_plausible_alternatives_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_DOC_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_does-it-follow-that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_does-it-follow-that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_explicit-graph-description2_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_stand-for_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_yes_no_question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_create_text_for_me_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_valid_binary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_stand-for_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_exercise_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_this_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_choose-the-most-appropriate-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_does-it-follow-that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_best_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_what_is_the_correct_ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_GPT-3-Style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_this_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_tldr_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_implicit-graph-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_Correct-the-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Generate-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_GPT-3-Style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_explicit-graph-description2_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_guaranteed-true_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_pick_correct_choice_index_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_best_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_non-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_choose_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_plausible_alternatives_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-Question-First_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_pick_correct_choice_index_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_rephrase_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_explicit-graph-description2_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Generate-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Generate-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Answer-Given-options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_does-it-follow-that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_stand-for_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_valid_binary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_True-or-False_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_coherent_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_Replace_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_valid_binary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_write_abstract_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_article_summary_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_pick_correct_choice_index_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_stand-for_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Choose-Story-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_rephrase_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_plausible_alternatives_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_explicit-graph-description2_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_pick_correct_choice_index_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_Replace_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_no-prompt-needed_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Choose-Story-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_yes_no_question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_very-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_after_reading_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_DOC_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_explicit-graph-description2_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_explicit-graph-description2_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_what_is_the_correct_ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_yes_no_question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_choose-the-most-appropriate-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_does-it-follow-that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_write_abstract_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_choose_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_does-it-follow-that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_create_text_for_me_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_explicit-graph-description2_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_cause_effect_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_coherent_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_this_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_does-underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_Correct-the-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Story-Continuation-and-Options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_coherent_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_True-or-False_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Novel-Correct-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Answer-Given-options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_valid_binary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_no-prompt-needed_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_tldr_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_create_text_for_me_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_write_abstract_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_DOC_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_explicit-graph-description2_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_rephrase_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_DOC_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_tldr_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_Correct-the-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_create_text_for_me_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_best_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_no-prompt-needed_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_cause_effect_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_should-assume_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_this_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_does-underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_non-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Answer-Given-options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_exercise_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_does-underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_write_abstract_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_Correct-the-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-Question-First_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_best_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-Question-First_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Answer-Given-options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_True-or-False_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_exercise_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_coherent_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Story-Continuation-and-Options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_stand-for_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_plausible_alternatives_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_no-prompt-needed_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Generate-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_coherent_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_GPT-3-Style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Story-Continuation-and-Options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_non-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_choose-the-most-appropriate-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_stand-for_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Choose-Story-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Generate-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_does-it-follow-that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-Question-First_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_choose_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_choose_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_Replace_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_Correct-the-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_exercise_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_rephrase_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_DOC_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_after_reading_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_rephrase_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_cause_effect_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_should-assume_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_Replace_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_should-assume_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_plausible_alternatives_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_exercise_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_create_text_for_me_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_this_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_does-it-follow-that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_pick_correct_choice_index_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_valid_binary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_DOC_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_tldr_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_very-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Novel-Correct-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_implicit-graph-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_rephrase_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Answer-Given-options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_very-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_this_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_does-it-follow-that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_after_reading_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_coherent_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_yes_no_question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_no-prompt-needed_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_implicit-graph-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_True-or-False_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_choose-the-most-appropriate-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_pick_correct_choice_index_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_should-assume_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_yes_no_question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_DOC_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_implicit-graph-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_choose_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Generate-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_does-it-follow-that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_article_summary_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_does-it-follow-that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_explicit-graph-description2_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_cause_effect_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_after_reading_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_after_reading_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_what_is_the_correct_ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_create_text_for_me_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_choose-the-most-appropriate-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_GPT-3-Style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_stand-for_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Choose-Story-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_does-underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_rephrase_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_cause_effect_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_article_summary_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Answer-Given-options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_this_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Choose-Story-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_tldr_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_non-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_tldr_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_cause_effect_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_DOC_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_does-it-follow-that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_tldr_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_choose-the-most-appropriate-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_DOC_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_coherent_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Story-Continuation-and-Options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_does-underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_summarize_above_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_create_text_for_me_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_should-assume_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_GPT-3-Style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_after_reading_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_choose-the-most-appropriate-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Novel-Correct-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_yes_no_question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_yes_no_question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Answer-Given-options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-Question-First_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_choose_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-Question-First_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_does-it-follow-that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_non-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_Correct-the-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_no-prompt-needed_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_should-assume_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Choose-Story-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_cause_effect_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_valid_binary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_write_abstract_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_this_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-Question-First_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_valid_binary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_what_is_the_correct_ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_write_abstract_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_True-or-False_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_yes_no_question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_DOC_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_pick_correct_choice_index_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_plausible_alternatives_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_create_text_for_me_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_does-it-follow-that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_write_abstract_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_what_is_the_correct_ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_DOC_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-Question-First_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Novel-Correct-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_stand-for_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Novel-Correct-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_valid_binary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_tldr_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_Correct-the-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_True-or-False_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_plausible_alternatives_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_no-prompt-needed_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_write_abstract_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_very-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_pick_correct_choice_index_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_stand-for_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_GPT-3-Style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_write_abstract_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_Correct-the-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_create_text_for_me_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_True-or-False_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_best_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_implicit-graph-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_what_is_the_correct_ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_tldr_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Novel-Correct-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_Correct-the-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_stand-for_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_cause_effect_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_this_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_pick_correct_choice_index_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_what_is_the_correct_ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_does-it-follow-that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_after_reading_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_very-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_does-underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_DOC_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_GPT-3-Style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Answer-Given-options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_does-it-follow-that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_GPT-3-Style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_Correct-the-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Choose-Story-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_does-it-follow-that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_explicit-graph-description2_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_implicit-graph-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_DOC_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_rephrase_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_True-or-False_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_coherent_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_what_is_the_correct_ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_what_is_the_correct_ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_this_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_DOC_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_best_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_coherent_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_create_text_for_me_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_article_summary_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_valid_binary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_very-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_should-assume_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_best_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_yes_no_question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_exercise_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_exercise_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_plausible_alternatives_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Novel-Correct-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_after_reading_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_cause_effect_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_no-prompt-needed_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-Question-First_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_Replace_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_True-or-False_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_plausible_alternatives_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_rephrase_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_choose-the-most-appropriate-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_exercise_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_rephrase_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_non-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_Replace_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Answer-Given-options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_create_text_for_me_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_Replace_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_choose-the-most-appropriate-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_choose_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_after_reading_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_cause_effect_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_after_reading_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_choose_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Story-Continuation-and-Options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_DOC_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_this_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_very-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_what_is_the_correct_ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_choose-the-most-appropriate-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Story-Continuation-and-Options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_Replace_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Generate-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Generate-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_non-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_what_is_the_correct_ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_Replace_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_summarize_above_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_GPT-3-Style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_True-or-False_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Story-Continuation-and-Options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_best_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_should-assume_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Answer-Given-options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_stand-for_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_coherent_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_Replace_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_valid_binary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_best_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_plausible_alternatives_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Choose-Story-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_stand-for_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_implicit-graph-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_exercise_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_tldr_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_create_text_for_me_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_what_is_the_correct_ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_coherent_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_cause_effect_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Answer-Given-options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_tldr_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Novel-Correct-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_best_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_very-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_should-assume_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_choose_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_this_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_valid_binary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_no-prompt-needed_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_article_summary_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Answer-Given-options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_guaranteed-true_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_article_summary_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_plausible_alternatives_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Story-Continuation-and-Options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_tldr_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_True-or-False_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_exercise_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_cause_effect_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-Question-First_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_choose-the-most-appropriate-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_very-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_does-it-follow-that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_write_abstract_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_does-it-follow-that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_article_summary_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_GPT-3-Style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Novel-Correct-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_choose_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_choose-the-most-appropriate-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_pick_correct_choice_index_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_guaranteed-true_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_write_abstract_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_write_abstract_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_yes_no_question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_stand-for_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_valid_binary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_guaranteed-true_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_valid_binary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_no-prompt-needed_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-Question-First_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-Question-First_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_very-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_Correct-the-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_does-underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_explicit-graph-description2_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_rephrase_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_explicit-graph-description2_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_does-it-follow-that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_pick_correct_choice_index_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Choose-Story-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_write_abstract_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_best_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_create_text_for_me_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_pick_correct_choice_index_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_tldr_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_guaranteed-true_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_does-it-follow-that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_valid_binary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_rephrase_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_write_abstract_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_no-prompt-needed_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_choose_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_coherent_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Answer-Given-options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_guaranteed-true_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Choose-Story-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_best_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_exercise_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_create_text_for_me_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_explicit-graph-description2_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_cause_effect_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_pick_correct_choice_index_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_True-or-False_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_choose_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_rephrase_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_tldr_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Generate-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_exercise_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_does-it-follow-that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_article_summary_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_yes_no_question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_should-assume_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_guaranteed-true_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_cause_effect_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Novel-Correct-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_Correct-the-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_coherent_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_after_reading_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_create_text_for_me_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_after_reading_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Generate-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_rephrase_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_pick_correct_choice_index_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_summarize_above_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_yes_no_question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Novel-Correct-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_summarize_above_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_guaranteed-true_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_Replace_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_implicit-graph-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_write_abstract_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_GPT-3-Style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_does-it-follow-that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_Replace_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_does-underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_implicit-graph-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_Replace_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_exercise_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_choose-the-most-appropriate-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_Replace_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_rephrase_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_should-assume_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_yes_no_question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_True-or-False_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Story-Continuation-and-Options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_article_summary_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_coherent_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_does-underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_summarize_above_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_exercise_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Story-Continuation-and-Options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_DOC_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_implicit-graph-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_Replace_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_guaranteed-true_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_this_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Novel-Correct-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_does-it-follow-that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_Replace_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_best_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_after_reading_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_this_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-Question-First_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-Question-First_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Generate-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_very-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_non-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_write_abstract_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_Correct-the-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_True-or-False_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_create_text_for_me_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_DOC_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Choose-Story-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_article_summary_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_implicit-graph-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_should-assume_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_summarize_above_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-Question-First_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-Question-First_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_write_abstract_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_cause_effect_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_choose_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_valid_binary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_implicit-graph-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_plausible_alternatives_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_write_abstract_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_tldr_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_yes_no_question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Generate-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_True-or-False_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_rephrase_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_guaranteed-true_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_GPT-3-Style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_no-prompt-needed_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_summarize_above_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Novel-Correct-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Novel-Correct-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_DOC_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_very-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_stand-for_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_explicit-graph-description2_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_summarize_above_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Story-Continuation-and-Options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_exercise_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_True-or-False_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_plausible_alternatives_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_no-prompt-needed_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_best_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_implicit-graph-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_GPT-3-Style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_this_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Novel-Correct-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_does-underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_stand-for_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_pick_correct_choice_index_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_implicit-graph-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_cause_effect_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_summarize_above_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_should-assume_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Novel-Correct-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_implicit-graph-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_create_text_for_me_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_Correct-the-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_stand-for_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_valid_binary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_DOC_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_pick_correct_choice_index_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_GPT-3-Style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_write_abstract_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_yes_no_question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_choose-the-most-appropriate-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_does-underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_stand-for_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_article_summary_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_article_summary_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_exercise_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Story-Continuation-and-Options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_Replace_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_this_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Answer-Given-options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_plausible_alternatives_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Choose-Story-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Story-Continuation-and-Options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_DOC_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_non-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_tldr_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_Replace_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_summarize_above_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_no-prompt-needed_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_summarize_above_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Answer-Given-options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_True-or-False_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Choose-Story-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Generate-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_choose-the-most-appropriate-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_guaranteed-true_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_guaranteed-true_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_cause_effect_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_choose_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Answer-Given-options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_choose_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_exercise_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Choose-Story-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_coherent_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Story-Continuation-and-Options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Story-Continuation-and-Options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_should-assume_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_GPT-3-Style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_no-prompt-needed_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Answer-Given-options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_guaranteed-true_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_article_summary_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_best_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_DOC_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_choose_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_coherent_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_rephrase_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_plausible_alternatives_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_coherent_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_GPT-3-Style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_this_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Choose-Story-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_stand-for_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_cause_effect_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_valid_binary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question-(Closed-Book)_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_article_summary_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_after_reading_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_guaranteed-true_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_exercise_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Novel-Correct-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_cause_effect_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_what_is_the_correct_ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_summarize_above_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_guaranteed-true_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_article_summary_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_valid_binary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_stand-for_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_yes_no_question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_rephrase_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_explicit-graph-description2_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-(Closed-Book)_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_very-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_coherent_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_choose_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_what_is_the_correct_ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_stand-for_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_summarize_above_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_summarize_above_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_best_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_stand-for_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_GPT-3-Style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_guaranteed-true_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Choose-Story-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_best_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Answer-Given-options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_does-underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_should-assume_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_coherent_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_DOC_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_True-or-False_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_what_is_the_correct_ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_tldr_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_summarize_above_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_this_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_yes_no_question_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_should-assume_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_Correct-the-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_does-underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_should-assume_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-wiki_lingua_en_write_abstract_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_exercise_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_create_text_for_me_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-Question-First_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_valid_binary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_implicit-graph-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_cause_effect_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_valid_binary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_summarize_above_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_Replace_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-Question-First_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_cause_effect_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_article_summary_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_article_summary_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_rephrase_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Answer-Given-options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_best_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_article_summary_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_non-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-Question-First_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_what_is_the_correct_ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_tldr_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_this_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_implicit-graph-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Generate-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_explicit-graph-description2_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Generate-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Answer-Given-options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Story-Continuation-and-Options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Choose-Story-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_should-assume_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_article_summary_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_Correct-the-solution_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_underscore-refer-to_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_rephrase_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_pick_correct_choice_index_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_explicit-graph-description2_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_cause_effect_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_what_is_the_correct_ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Novel-Correct-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_implicit-graph-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_pick_correct_choice_index_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_True-or-False_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_non-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-(Closed-Book)_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_cause_effect_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_explicit-graph-description2_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_create_text_for_me_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_choose_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_True-or-False_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_after_reading_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_non-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_exercise_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_implicit-graph-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_no-prompt-needed_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_what_is_the_correct_ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Story-Continuation-and-Options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_choose-the-most-appropriate-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Generate-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_GPT-3-Style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_rephrase_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_i_am_hesitating_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_choose_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_pick_correct_choice_index_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_coherent_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_choose_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_does-underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_what_is_the_correct_ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-Question-First_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_Correct-the-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_plausible_alternatives_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_pick_correct_choice_index_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_no-prompt-needed_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_summarize_above_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_after_reading_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_non-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_after_reading_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_boolq_GPT-3-Style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_choose-the-most-appropriate-solution_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Novel-Correct-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_no-prompt-needed_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Story-Continuation-and-Options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Choose-Story-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_plausible_alternatives_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-Question-First_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_True-or-False_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_summarize_this_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_summarize_above_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_tldr_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_non-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_coherent_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Story-Continuation-and-Options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Answer-Given-options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_non-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_does-underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_pick_the_most_correct_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_after_reading_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_after_reading_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_True-or-False_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_this_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_pick_the_most_correct_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_Correct-the-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question-(Closed-Book)_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_should-assume_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_summarize_above_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_valid_binary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Answer-Given-options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_Replace_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_summarize_above_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Generate-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_summarize_above_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Generate-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_non-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_yes_no_question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_cause_effect_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_very-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_best_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_no-prompt-needed_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_choose_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_DOC_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_article_summary_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_cause_effect_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_Correct-the-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_yes_no_question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Novel-Correct-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_multiple_choice_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_after_reading_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Direct-Question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_very-explicit-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_yes_no_question_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_choose_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_what_is_the_correct_ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_rephrase_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_choose_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_multiple_choice_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_implicit-graph-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_coherent_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_stand-for_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_article_summary_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_plausible_alternatives_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_does-underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_this_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_non-explicit-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Choose-Story-Ending_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_coherent_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Story-Continuation-and-Options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_justified-in-saying_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Answer-Given-options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_very-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_GPT-3-Style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_write_abstract_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_explicit-graph-description2_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_pick_correct_choice_index_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Generate-Ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_coherent_text_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Generate-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Generate-Ending_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_this_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_GPT-3-Style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_summarize_above_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_qa_options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_choose-the-most-appropriate-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_True-or-False_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_very-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_after_reading_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Generate-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_should-assume_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_choose-the-most-appropriate-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_best_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_summarize_this_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_should-assume_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_plausible_alternatives_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_rephrase_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_valid_binary_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_implicit-graph-description_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Direct-Question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_summarize_above_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_qa_options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_coherent_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_True-or-False_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_rephrase_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_multiple_choice_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_rephrase_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_coherent_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Novel-Correct-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_choose-the-most-appropriate-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-Question-First_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_e2e_nlg_cleaned_text_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_yes_no_question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_implicit-graph-description_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_no-prompt-needed_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_i_am_hesitating_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Choose-Story-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_challenge_multiple_choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_yes_no_question_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Choose-Story-Ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Answer-Given-options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Generate-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_implicit-graph-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_guaranteed-possible-impossible_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_no-prompt-needed_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_cause_effect_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_no-prompt-needed_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_challenge_pick_the_most_correct_option_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_heres_a_problem_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_heres_a_problem_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_best_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_this_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_choose_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_very-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_yes_no_question_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_best_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_guaranteed-possible-impossible_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_i_am_hesitating_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Generate-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_pick_the_most_correct_option_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_pick_the_most_correct_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_choose_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_GPT-3-style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_choose-the-most-appropriate-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_create_text_for_me_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_explicit-graph-description2_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_does-underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_GPT-3-Style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_after_reading_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_plausible_alternatives_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_winogrande_stand-for_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_challenge_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Generate-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_choose-the-most-appropriate-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Answer-Given-options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_GPT-3-Style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_tldr_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Multiple-Choice-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_Correct-the-solution_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_after_reading_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_valid_binary_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_very-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_summarize_DOC_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_cause_effect_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_explicit-graph-description2_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_should-assume_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_True-or-False_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_boolq_after_reading_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_create_text_for_me_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_choose-the-most-appropriate-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_heres_a_problem_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_i_am_hesitating_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-Question-First_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_can-we-infer_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-Question-First_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_does-underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_best_option_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_exercise_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r3_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_should-assume_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_article_summary_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_explicit-graph-description2_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_no-prompt-needed_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_does-underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r1_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_exercise_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_story_cloze_2016_Choose-Story-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Story-Continuation-and-Options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_create_text_for_me_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_very-explicit-description_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_choose-the-most-appropriate-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Answer-Given-options_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_write_abstract_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_gem_xsum_DOC_tldr_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_GPT-3-Style_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_text_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r3_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_plausible_alternatives_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_story_cloze_2016_Generate-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_article_summary_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_best_option_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Story-Continuation-and-Options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_qa_options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_arc_easy_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_after_reading_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Multiple-Choice-Question-First_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_heres_a_problem_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_best_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_justified-in-saying_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_GPT-3-Style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_can-we-infer_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_summarize_above_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_valid_binary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_DOC_tldr_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_DOC_tldr_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_create_text_for_me_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_sciq_Direct-Question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_gem_xsum_summarize_this_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_does-underscore-refer-to_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_cb_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_MNLI-crowdsource_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Choose-Story-Ending_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-wiki_lingua_en_write_abstract_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_exercise_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_copa_plausible_alternatives_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_sciq_Multiple-Choice-Question-First_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_copa_plausible_alternatives_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_cb_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_qa_options_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_write_abstract_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Novel-Correct-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_MNLI-crowdsource_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_sciq_Direct-Question_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_anli_r2_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_pick_correct_choice_index_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_MNLI-crowdsource_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_write_abstract_en_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question-(Closed-Book)_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_does-underscore-refer-to_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_summarize_above_en_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_True-or-False_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_exercise_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_GPT-3-style_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_superglue_rte_should-assume_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_can-we-infer_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_story_cloze_2016_Answer-Given-options_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_very-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r1_justified-in-saying_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_guaranteed-possible-impossible_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_what_is_the_correct_ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_boolq_exercise_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_boolq_exercise_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-wiki_lingua_en_write_abstract_en_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_qa_options_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_very-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_plausible_alternatives_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_explicit-graph-description2_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_can-we-infer_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_justified-in-saying_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r1_can-we-infer_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_story_cloze_2016_Answer-Given-options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice-Question-First_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_summarize_above_en_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_after_reading_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_multiple_choice_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_gem_xsum_DOC_tldr_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_no-prompt-needed_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_does-underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_underscore-refer-to_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_cb_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r3_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_choose-the-most-appropriate-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_piqa_Correct-the-solution_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_e2e_nlg_cleaned_text_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_winogrande_True-or-False_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_implicit-graph-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-web_nlg_en_non-explicit-description_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_copa_best_option_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_piqa_pick_correct_choice_index_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_guaranteed-true_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_exercise_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_heres_a_problem_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_GEM-web_nlg_en_implicit-graph-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_MNLI-crowdsource_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_anli_r2_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_GEM-web_nlg_en_non-explicit-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_cb_guaranteed-possible-impossible_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_cause_effect_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_create_text_for_me_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_what_is_the_correct_ending_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r3_justified-in-saying_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Direct-Question_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_arc_easy_i_am_hesitating_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_GEM-wiki_lingua_en_summarize_above_en_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_cb_can-we-infer_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_gem_xsum_summarize_DOC_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_sciq_Multiple-Choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-web_nlg_en_non-explicit-description_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Story-Continuation-and-Options_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_multiple_choice_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_guaranteed-possible-impossible_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r3_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_superglue_rte_GPT-3-style_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_e2e_nlg_cleaned_create_text_for_me_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_GPT-3-style_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r2_GPT-3-style_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_challenge_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_superglue_rte_GPT-3-style_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r1_justified-in-saying_3.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_anli_r1_MNLI-crowdsource_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_story_cloze_2016_Choose-Story-Ending_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_piqa_what_is_the_correct_ending_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_winogrande_Replace_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_piqa_choose-the-most-appropriate-solution_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_piqa_Correct-the-solution_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_sciq_Multiple-Choice-(Closed-Book)_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_GEM-wiki_lingua_en_rephrase_en_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_superglue_rte_guaranteed-true_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_copa_plausible_alternatives_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_arc_easy_qa_options_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_easy_i_am_hesitating_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_anli_r2_MNLI-crowdsource_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_underscore-refer-to_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_winogrande_Replace_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_winogrande_does-underscore-refer-to_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_GEM-web_nlg_en_implicit-graph-description_5.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_arc_challenge_pick_the_most_correct_option_1.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b17boscar/eval/examples.4b284b17boscar_boolq_valid_binary_2.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b21boscar/eval/examples.4b284b21boscar_superglue_rte_should-assume_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b28boscar/eval/examples.4b284b28boscar_anli_r2_guaranteed-possible-impossible_0.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b42boscar/eval/examples.4b284b42boscar_copa_choose_4.jsonl filter=lfs diff=lfs merge=lfs -text +4b284b12boscar/eval/examples.4b284b12boscar_arc_easy_heres_a_problem_3.jsonl filter=lfs diff=lfs merge=lfs -text