[ { "name": "stackexchange_title_body/skeptics.stackexchange.com.jsonl.gz", "lines": 10009, "weight": 3 }, { "name": "stackexchange_Title_Answer/islam.stackexchange.com.jsonl.gz", "lines": 10052, "weight": 3 }, { "name": "stackexchange_Title_Answer/anime.stackexchange.com.jsonl.gz", "lines": 10131, "weight": 3 }, { "name": "stackexchange_title_body/writers.stackexchange.com.jsonl.gz", "lines": 10157, "weight": 3 }, { "name": "stackexchange_title_body/astronomy.stackexchange.com.jsonl.gz", "lines": 10462, "weight": 3 }, { "name": "stackexchange_title_body/vi.stackexchange.com.jsonl.gz", "lines": 10551, "weight": 3 }, { "name": "stackexchange_Title_Answer/french.stackexchange.com.jsonl.gz", "lines": 10578, "weight": 3 }, { "name": "stackexchange_title_body/cstheory.stackexchange.com.jsonl.gz", "lines": 10642, "weight": 3 }, { "name": "stackexchange_Title_Answer/civicrm.stackexchange.com.jsonl.gz", "lines": 10648, "weight": 3 }, { "name": "stackexchange_Title_Answer/expressionengine.stackexchange.com.jsonl.gz", "lines": 10742, "weight": 3 }, { "name": "stackexchange_title_body/engineering.stackexchange.com.jsonl.gz", "lines": 10753, "weight": 3 }, { "name": "stackexchange_Title_Answer/history.stackexchange.com.jsonl.gz", "lines": 10766, "weight": 3 }, { "name": "stackexchange_title_body/french.stackexchange.com.jsonl.gz", "lines": 10794, "weight": 3 }, { "name": "stackexchange_Title_Answer/politics.stackexchange.com.jsonl.gz", "lines": 11047, "weight": 3 }, { "name": "stackexchange_title_body/economics.stackexchange.com.jsonl.gz", "lines": 11115, "weight": 3 }, { "name": "stackexchange_Title_Answer/craftcms.stackexchange.com.jsonl.gz", "lines": 11236, "weight": 3 }, { "name": "stackexchange_title_body/anime.stackexchange.com.jsonl.gz", "lines": 11444, "weight": 3 }, { "name": "stackexchange_Title_Answer/christianity.stackexchange.com.jsonl.gz", "lines": 11498, "weight": 3 }, { "name": "stackexchange_Title_Answer/softwarerecs.stackexchange.com.jsonl.gz", "lines": 11761, "weight": 3 }, { "name": "stackexchange_Title_Answer/boardgames.stackexchange.com.jsonl.gz", "lines": 11805, "weight": 3 }, { "name": "stackexchange_title_body/islam.stackexchange.com.jsonl.gz", "lines": 11853, "weight": 3 }, { "name": "stackexchange_title_body/expressionengine.stackexchange.com.jsonl.gz", "lines": 11866, "weight": 3 }, { "name": "stackexchange_title_body/politics.stackexchange.com.jsonl.gz", "lines": 11894, "weight": 3 }, { "name": "stackexchange_title_body/history.stackexchange.com.jsonl.gz", "lines": 12021, "weight": 3 }, { "name": "stackexchange_title_body/christianity.stackexchange.com.jsonl.gz", "lines": 12108, "weight": 3 }, { "name": "stackexchange_title_body/boardgames.stackexchange.com.jsonl.gz", "lines": 12149, "weight": 3 }, { "name": "stackexchange_title_body/civicrm.stackexchange.com.jsonl.gz", "lines": 12543, "weight": 3 }, { "name": "stackexchange_title_body/craftcms.stackexchange.com.jsonl.gz", "lines": 12574, "weight": 3 }, { "name": "stackexchange_Title_Answer/networkengineering.stackexchange.com.jsonl.gz", "lines": 12590, "weight": 3 }, { "name": "stackexchange_Title_Answer/space.stackexchange.com.jsonl.gz", "lines": 12893, "weight": 3 }, { "name": "stackexchange_Title_Answer/quant.stackexchange.com.jsonl.gz", "lines": 12933, "weight": 3 }, { "name": "stackexchange_Title_Answer/philosophy.stackexchange.com.jsonl.gz", "lines": 13114, "weight": 3 }, { "name": "stackexchange_Title_Answer/gardening.stackexchange.com.jsonl.gz", "lines": 13246, "weight": 3 }, { "name": "stackexchange_title_body/hinduism.stackexchange.com.jsonl.gz", "lines": 13450, "weight": 4 }, { "name": "stackexchange_title_body/networkengineering.stackexchange.com.jsonl.gz", "lines": 13454, "weight": 4 }, { "name": "stackexchange_Title_Answer/german.stackexchange.com.jsonl.gz", "lines": 13733, "weight": 4 }, { "name": "stackexchange_title_body/german.stackexchange.com.jsonl.gz", "lines": 13950, "weight": 4 }, { "name": "stackexchange_title_body/philosophy.stackexchange.com.jsonl.gz", "lines": 14829, "weight": 4 }, { "name": "stackexchange_title_body/gardening.stackexchange.com.jsonl.gz", "lines": 15136, "weight": 4 }, { "name": "stackexchange_title_body/space.stackexchange.com.jsonl.gz", "lines": 15142, "weight": 4 }, { "name": "stackexchange_Title_Answer/bicycles.stackexchange.com.jsonl.gz", "lines": 15708, "weight": 4 }, { "name": "stackexchange_Title_Answer/law.stackexchange.com.jsonl.gz", "lines": 16133, "weight": 4 }, { "name": "stackexchange_Title_Answer/arduino.stackexchange.com.jsonl.gz", "lines": 16281, "weight": 4 }, { "name": "stackexchange_title_body/bicycles.stackexchange.com.jsonl.gz", "lines": 16353, "weight": 4 }, { "name": "stackexchange_Title_Answer/emacs.stackexchange.com.jsonl.gz", "lines": 16830, "weight": 4 }, { "name": "stackexchange_title_body/quant.stackexchange.com.jsonl.gz", "lines": 17261, "weight": 4 }, { "name": "stackexchange_Title_Answer/dsp.stackexchange.com.jsonl.gz", "lines": 17430, "weight": 4 }, { "name": "stackexchange_Title_Answer/puzzling.stackexchange.com.jsonl.gz", "lines": 17448, "weight": 4 }, { "name": "stackexchange_title_body/puzzling.stackexchange.com.jsonl.gz", "lines": 17851, "weight": 5 }, { "name": "stackexchange_title_body/law.stackexchange.com.jsonl.gz", "lines": 17941, "weight": 5 }, { "name": "stackexchange_Title_Answer/movies.stackexchange.com.jsonl.gz", "lines": 18243, "weight": 5 }, { "name": "stackexchange_Title_Answer/mechanics.stackexchange.com.jsonl.gz", "lines": 18613, "weight": 5 }, { "name": "stackexchange_Title_Answer/aviation.stackexchange.com.jsonl.gz", "lines": 18755, "weight": 5 }, { "name": "stackexchange_Title_Answer/biology.stackexchange.com.jsonl.gz", "lines": 19277, "weight": 5 }, { "name": "stackexchange_Title_Answer/crypto.stackexchange.com.jsonl.gz", "lines": 19404, "weight": 5 }, { "name": "stackexchange_title_body/arduino.stackexchange.com.jsonl.gz", "lines": 19553, "weight": 5 }, { "name": "stackexchange_Title_Answer/music.stackexchange.com.jsonl.gz", "lines": 19936, "weight": 5 }, { "name": "stackexchange_title_body/aviation.stackexchange.com.jsonl.gz", "lines": 20139, "weight": 5 }, { "name": "stackexchange_title_body/softwarerecs.stackexchange.com.jsonl.gz", "lines": 20142, "weight": 5 }, { "name": "stackexchange_title_body/movies.stackexchange.com.jsonl.gz", "lines": 20181, "weight": 5 }, { "name": "stackexchange_Title_Answer/datascience.stackexchange.com.jsonl.gz", "lines": 20503, "weight": 5 }, { "name": "stackexchange_title_body/music.stackexchange.com.jsonl.gz", "lines": 20636, "weight": 5 }, { "name": "stackexchange_Title_Answer/japanese.stackexchange.com.jsonl.gz", "lines": 20948, "weight": 5 }, { "name": "stackexchange_title_body/emacs.stackexchange.com.jsonl.gz", "lines": 21055, "weight": 5 }, { "name": "stackexchange_title_body/dsp.stackexchange.com.jsonl.gz", "lines": 21252, "weight": 5 }, { "name": "stackexchange_title_body/japanese.stackexchange.com.jsonl.gz", "lines": 22056, "weight": 5 }, { "name": "stackexchange_Title_Answer/bitcoin.stackexchange.com.jsonl.gz", "lines": 22474, "weight": 6 }, { "name": "stackexchange_Title_Answer/cooking.stackexchange.com.jsonl.gz", "lines": 22641, "weight": 6 }, { "name": "stackexchange_title_body/mechanics.stackexchange.com.jsonl.gz", "lines": 22868, "weight": 6 }, { "name": "stackexchange_Title_Answer/photo.stackexchange.com.jsonl.gz", "lines": 23204, "weight": 6 }, { "name": "stackexchange_title_body/crypto.stackexchange.com.jsonl.gz", "lines": 23231, "weight": 6 }, { "name": "stackexchange_title_body/cooking.stackexchange.com.jsonl.gz", "lines": 23705, "weight": 6 }, { "name": "stackexchange_title_body/photo.stackexchange.com.jsonl.gz", "lines": 23753, "weight": 6 }, { "name": "stackexchange_Title_Answer/workplace.stackexchange.com.jsonl.gz", "lines": 24012, "weight": 6 }, { "name": "stackexchange_Title_Answer/meta.stackoverflow.com.jsonl.gz", "lines": 24044, "weight": 6 }, { "name": "stackexchange_Title_Answer/raspberrypi.stackexchange.com.jsonl.gz", "lines": 24143, "weight": 6 }, { "name": "stackexchange_title_body/workplace.stackexchange.com.jsonl.gz", "lines": 24189, "weight": 6 }, { "name": "stackexchange_title_body/biology.stackexchange.com.jsonl.gz", "lines": 24447, "weight": 6 }, { "name": "stackexchange_Title_Answer/webapps.stackexchange.com.jsonl.gz", "lines": 24867, "weight": 6 }, { "name": "stackexchange_title_body/bitcoin.stackexchange.com.jsonl.gz", "lines": 25374, "weight": 6 }, { "name": "stackexchange_Title_Answer/judaism.stackexchange.com.jsonl.gz", "lines": 26085, "weight": 6 }, { "name": "stackexchange_Title_Answer/ethereum.stackexchange.com.jsonl.gz", "lines": 26124, "weight": 6 }, { "name": "stackexchange_Title_Answer/worldbuilding.stackexchange.com.jsonl.gz", "lines": 26210, "weight": 6 }, { "name": "stackexchange_title_body/worldbuilding.stackexchange.com.jsonl.gz", "lines": 26763, "weight": 7 }, { "name": "stackexchange_Title_Answer/chemistry.stackexchange.com.jsonl.gz", "lines": 27061, "weight": 7 }, { "name": "stackexchange_title_body/datascience.stackexchange.com.jsonl.gz", "lines": 27397, "weight": 7 }, { "name": "stackexchange_Title_Answer/graphicdesign.stackexchange.com.jsonl.gz", "lines": 28083, "weight": 7 }, { "name": "stackexchange_Title_Answer/ux.stackexchange.com.jsonl.gz", "lines": 28901, "weight": 7 }, { "name": "stackexchange_title_body/ux.stackexchange.com.jsonl.gz", "lines": 29403, "weight": 7 }, { "name": "stackexchange_Title_Answer/money.stackexchange.com.jsonl.gz", "lines": 29404, "weight": 7 }, { "name": "stackexchange_title_body/webapps.stackexchange.com.jsonl.gz", "lines": 29697, "weight": 7 }, { "name": "stackexchange_Title_Answer/cs.stackexchange.com.jsonl.gz", "lines": 30010, "weight": 7 }, { "name": "stackexchange_title_body/graphicdesign.stackexchange.com.jsonl.gz", "lines": 30233, "weight": 7 }, { "name": "stackexchange_Title_Answer/webmasters.stackexchange.com.jsonl.gz", "lines": 30370, "weight": 7 }, { "name": "stackexchange_title_body/raspberrypi.stackexchange.com.jsonl.gz", "lines": 30625, "weight": 7 }, { "name": "stackexchange_title_body/money.stackexchange.com.jsonl.gz", "lines": 32021, "weight": 8 }, { "name": "stackexchange_title_body/judaism.stackexchange.com.jsonl.gz", "lines": 32028, "weight": 8 }, { "name": "stackexchange_Title_Answer/academia.stackexchange.com.jsonl.gz", "lines": 32137, "weight": 8 }, { "name": "stackexchange_title_body/ethereum.stackexchange.com.jsonl.gz", "lines": 32760, "weight": 8 }, { "name": "stackexchange_title_body/academia.stackexchange.com.jsonl.gz", "lines": 34331, "weight": 8 }, { "name": "stackexchange_title_body/chemistry.stackexchange.com.jsonl.gz", "lines": 34506, "weight": 8 }, { "name": "stackexchange_title_body/webmasters.stackexchange.com.jsonl.gz", "lines": 34559, "weight": 8 }, { "name": "stackexchange_title_body/meta.stackoverflow.com.jsonl.gz", "lines": 36456, "weight": 9 }, { "name": "stackexchange_Title_Answer/travel.stackexchange.com.jsonl.gz", "lines": 36533, "weight": 9 }, { "name": "stackexchange_Title_Answer/android.stackexchange.com.jsonl.gz", "lines": 38077, "weight": 9 }, { "name": "stackexchange_title_body/cs.stackexchange.com.jsonl.gz", "lines": 38314, "weight": 9 }, { "name": "stackexchange_Title_Answer/gamedev.stackexchange.com.jsonl.gz", "lines": 40154, "weight": 10 }, { "name": "stackexchange_Title_Answer/rpg.stackexchange.com.jsonl.gz", "lines": 40435, "weight": 10 }, { "name": "stackexchange_title_body/travel.stackexchange.com.jsonl.gz", "lines": 41227, "weight": 10 }, { "name": "stackexchange_Title_Answer/codereview.stackexchange.com.jsonl.gz", "lines": 41748, "weight": 10 }, { "name": "stackexchange_title_body/rpg.stackexchange.com.jsonl.gz", "lines": 42303, "weight": 10 }, { "name": "stackexchange_title_body/codereview.stackexchange.com.jsonl.gz", "lines": 45765, "weight": 11 }, { "name": "stackexchange_title_body/gamedev.stackexchange.com.jsonl.gz", "lines": 46485, "weight": 11 }, { "name": "stackexchange_Title_Answer/softwareengineering.stackexchange.com.jsonl.gz", "lines": 51326, "weight": 12 }, { "name": "stackexchange_Title_Answer/security.stackexchange.com.jsonl.gz", "lines": 51355, "weight": 12 }, { "name": "stackexchange_title_body/android.stackexchange.com.jsonl.gz", "lines": 51608, "weight": 12 }, { "name": "stackexchange_Title_Answer/diy.stackexchange.com.jsonl.gz", "lines": 52896, "weight": 12 }, { "name": "stackexchange_title_body/softwareengineering.stackexchange.com.jsonl.gz", "lines": 53942, "weight": 13 }, { "name": "stackexchange_Title_Answer/blender.stackexchange.com.jsonl.gz", "lines": 54153, "weight": 13 }, { "name": "stackexchange_Title_Answer/scifi.stackexchange.com.jsonl.gz", "lines": 54805, "weight": 13 }, { "name": "stackexchange_title_body/security.stackexchange.com.jsonl.gz", "lines": 58000, "weight": 14 }, { "name": "stackexchange_Title_Answer/mathematica.stackexchange.com.jsonl.gz", "lines": 59895, "weight": 14 }, { "name": "stackexchange_title_body/diy.stackexchange.com.jsonl.gz", "lines": 60083, "weight": 14 }, { "name": "stackexchange_Title_Answer/meta.stackexchange.com.jsonl.gz", "lines": 60744, "weight": 14 }, { "name": "stackexchange_title_body/scifi.stackexchange.com.jsonl.gz", "lines": 61528, "weight": 14 }, { "name": "stackexchange_Title_Answer/drupal.stackexchange.com.jsonl.gz", "lines": 67817, "weight": 16 }, { "name": "stackexchange_Title_Answer/dba.stackexchange.com.jsonl.gz", "lines": 71449, "weight": 17 }, { "name": "stackexchange_title_body/mathematica.stackexchange.com.jsonl.gz", "lines": 73131, "weight": 17 }, { "name": "stackexchange_Title_Answer/ell.stackexchange.com.jsonl.gz", "lines": 77892, "weight": 18 }, { "name": "stackexchange_Title_Answer/magento.stackexchange.com.jsonl.gz", "lines": 79241, "weight": 18 }, { "name": "stackexchange_title_body/drupal.stackexchange.com.jsonl.gz", "lines": 79717, "weight": 18 }, { "name": "stackexchange_Title_Answer/sharepoint.stackexchange.com.jsonl.gz", "lines": 80420, "weight": 19 }, { "name": "stackexchange_title_body/blender.stackexchange.com.jsonl.gz", "lines": 80766, "weight": 19 }, { "name": "stackexchange_title_body/dba.stackexchange.com.jsonl.gz", "lines": 81871, "weight": 19 }, { "name": "stackexchange_Title_Answer/gaming.stackexchange.com.jsonl.gz", "lines": 82887, "weight": 19 }, { "name": "stackexchange_title_body/ell.stackexchange.com.jsonl.gz", "lines": 83271, "weight": 19 }, { "name": "stackexchange_title_body/meta.stackexchange.com.jsonl.gz", "lines": 83510, "weight": 19 }, { "name": "stackexchange_Title_Answer/wordpress.stackexchange.com.jsonl.gz", "lines": 83621, "weight": 19 }, { "name": "stackexchange_Title_Answer/mathoverflow.net.jsonl.gz", "lines": 85289, "weight": 20 }, { "name": "stackexchange_Title_Answer/salesforce.stackexchange.com.jsonl.gz", "lines": 87272, "weight": 20 }, { "name": "stackexchange_title_body/gaming.stackexchange.com.jsonl.gz", "lines": 88912, "weight": 21 }, { "name": "stackexchange_Title_Answer/apple.stackexchange.com.jsonl.gz", "lines": 92487, "weight": 21 }, { "name": "stackexchange_title_body/sharepoint.stackexchange.com.jsonl.gz", "lines": 94011, "weight": 22 }, { "name": "stackexchange_title_body/magento.stackexchange.com.jsonl.gz", "lines": 99991, "weight": 23 }, { "name": "stackexchange_Title_Answer/gis.stackexchange.com.jsonl.gz", "lines": 100254, "weight": 23 }, { "name": "stackexchange_title_body/wordpress.stackexchange.com.jsonl.gz", "lines": 100474, "weight": 23 }, { "name": "stackexchange_Title_Answer/english.stackexchange.com.jsonl.gz", "lines": 100640, "weight": 23 }, { "name": "stackexchange_title_body/salesforce.stackexchange.com.jsonl.gz", "lines": 105260, "weight": 24 }, { "name": "stackexchange_title_body/english.stackexchange.com.jsonl.gz", "lines": 109522, "weight": 25 }, { "name": "stackexchange_title_body/apple.stackexchange.com.jsonl.gz", "lines": 110622, "weight": 25 }, { "name": "stackexchange_Title_Answer/stats.stackexchange.com.jsonl.gz", "lines": 115679, "weight": 27 }, { "name": "stackexchange_title_body/mathoverflow.net.jsonl.gz", "lines": 120851, "weight": 28 }, { "name": "stackexchange_Title_Answer/electronics.stackexchange.com.jsonl.gz", "lines": 129494, "weight": 30 }, { "name": "stackexchange_title_body/gis.stackexchange.com.jsonl.gz", "lines": 131000, "weight": 30 }, { "name": "stackexchange_Title_Answer/physics.stackexchange.com.jsonl.gz", "lines": 141230, "weight": 32 }, { "name": "stackexchange_title_body/electronics.stackexchange.com.jsonl.gz", "lines": 143582, "weight": 33 }, { "name": "TriviaQA_pairs.jsonl.gz", "lines": 73346, "weight": 34 }, { "name": "stackexchange_Title_Answer/unix.stackexchange.com.jsonl.gz", "lines": 155414, "weight": 36 }, { "name": "stackexchange_Title_Answer/tex.stackexchange.com.jsonl.gz", "lines": 171628, "weight": 39 }, { "name": "squad_pairs.jsonl.gz", "lines": 87599, "weight": 40 }, { "name": "stackexchange_title_body/physics.stackexchange.com.jsonl.gz", "lines": 173307, "weight": 40 }, { "name": "stackexchange_title_body/stats.stackexchange.com.jsonl.gz", "lines": 173466, "weight": 40 }, { "name": "stackexchange_title_body/unix.stackexchange.com.jsonl.gz", "lines": 185997, "weight": 42 }, { "name": "NQ-train_pairs.jsonl.gz", "lines": 100231, "weight": 46 }, { "name": "stackexchange_title_body/tex.stackexchange.com.jsonl.gz", "lines": 202954, "weight": 46 }, { "name": "quora_duplicates_triplets.jsonl.gz", "lines": 103663, "weight": 47 }, { "name": "stackexchange_Title_Answer/serverfault.com.jsonl.gz", "lines": 238507, "weight": 54 }, { "name": "stackexchange_Title_Answer/askubuntu.com.jsonl.gz", "lines": 267135, "weight": 61 }, { "name": "stackexchange_title_body/serverfault.com.jsonl.gz", "lines": 270904, "weight": 62 }, { "name": "stackexchange_duplicate_questions_title_title.jsonl.gz", "lines": 304525, "weight": 69 }, { "name": "stackexchange_title_body/askubuntu.com.jsonl.gz", "lines": 347925, "weight": 79 }, { "name": "stackexchange_Title_Answer/superuser.com.jsonl.gz", "lines": 352610, "weight": 80 }, { "name": "stackexchange_title_body/superuser.com.jsonl.gz", "lines": 435463, "weight": 99 }, { "name": "stackexchange_title_body/small_stackexchanges.jsonl.gz", "lines": 448146, "weight": 102 }, { "name": "stackexchange_Title_Answer/small_stackexchanges.jsonl.gz", "lines": 460256, "weight": 104 }, { "name": "eli5_question_answer.jsonl.gz", "lines": 325475, "weight": 147 }, { "name": "yahoo_answers_title_question.jsonl.gz", "lines": 659896, "weight": 149 }, { "name": "PAQ_pairs.jsonl.gz", "lines": 64371441, "weight": 150 }, { "name": "WikiAnswers_pairs.jsonl.gz", "lines": 77427422, "weight": 150 }, { "name": "stackexchange_Title_Answer/math.stackexchange.com.jsonl.gz", "lines": 1100953, "weight": 226 }, { "name": "yahoo_answers_title_answer.jsonl.gz", "lines": 1198260, "weight": 226 }, { "name": "stackexchange_title_body/math.stackexchange.com.jsonl.gz", "lines": 1338443, "weight": 226 }, { "name": "stackexchange_Title_Answer/stackoverflow.com-Posts.jsonl.gz", "lines": 15768211, "weight": 226 }, { "name": "stackexchange_title_body/stackoverflow.com-Posts.jsonl.gz", "lines": 18562443, "weight": 226 }, { "name": "searchQA_question_top5_snippets_merged.jsonl.gz", "lines": 582261, "weight": 263 }, { "name": "amazon-qa-train-pairs.jsonl.gz", "lines": 2448839, "weight": 451 }, { "name": "gooaq_pairs.jsonl.gz", "lines": 3012496, "weight": 451 }, { "name": "msmarco-query_passage_negative_v2.jsonl.gz", "lines": 17579773, "weight": 1000 } ]