Muennighoff's picture
Add
9fa0f77
raw
history blame
No virus
28 kB
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3552258551749086, "bleu_stderr": 0.02004694008107349, "rouge1_fmeasure": 0.09756985013732229, "rouge1_fmeasure_stderr": 0.0019859335153510982, "rouge1_precision": 0.07050133636806707, "rouge1_precision_stderr": 0.002333415676412846, "rouge1_recall": 0.28446739915287816, "rouge1_recall_stderr": 0.00508507867804917, "rouge2_fmeasure": 0.043506125605077994, "rouge2_fmeasure_stderr": 0.0012188241069113202, "rouge2_precision": 0.030757559038758858, "rouge2_precision_stderr": 0.0013508528253275045, "rouge2_recall": 0.13243423248660713, "rouge2_recall_stderr": 0.003309647236077234, "rougeL_fmeasure": 0.09211119558985698, "rougeL_fmeasure_stderr": 0.0018415131593686243, "rougeL_precision": 0.0666262101718174, "rougeL_precision_stderr": 0.002246557443572289, "rougeL_recall": 0.2713467656341814, "rougeL_recall_stderr": 0.004908738323537121, "rougeLsum_fmeasure": 0.0909840574356387, "rougeLsum_fmeasure_stderr": 0.0018721336661780886, "rougeLsum_precision": 0.06617315282201941, "rougeLsum_precision_stderr": 0.0022690978668772816, "rougeLsum_recall": 0.2645417006842324, "rougeLsum_recall_stderr": 0.004684946802992825}}, "1": {"PALM_prompt": {"bleu": 0.455214213531198, "bleu_stderr": 0.027035455129998113, "rouge1_fmeasure": 0.12895359157667396, "rouge1_fmeasure_stderr": 0.0030401563578052807, "rouge1_precision": 0.10632219422720153, "rouge1_precision_stderr": 0.0035658627377499956, "rouge1_recall": 0.2768550528667316, "rouge1_recall_stderr": 0.004832345662545228, "rouge2_fmeasure": 0.06090727845863285, "rouge2_fmeasure_stderr": 0.0019209569415793166, "rouge2_precision": 0.04940516839667132, "rouge2_precision_stderr": 0.0021584007358498585, "rouge2_recall": 0.13404371723129116, "rouge2_recall_stderr": 0.003324815594078369, "rougeL_fmeasure": 0.11713897308464187, "rougeL_fmeasure_stderr": 0.0026334790087808417, "rougeL_precision": 0.09546267515845965, "rougeL_precision_stderr": 0.003141923276845849, "rougeL_recall": 0.25843481586517253, "rougeL_recall_stderr": 0.004474300115661777, "rougeLsum_fmeasure": 0.11922109901669682, "rougeLsum_fmeasure_stderr": 0.002697373964352153, "rougeLsum_precision": 0.09758720980677024, "rougeLsum_precision_stderr": 0.0032165997299972056, "rougeLsum_recall": 0.2609559973772103, "rougeLsum_recall_stderr": 0.00448462250486365}}, "2": {"PALM_prompt": {"bleu": 0.43672089515970186, "bleu_stderr": 0.021621818007392418, "rouge1_fmeasure": 0.15107097447841042, "rouge1_fmeasure_stderr": 0.0035335849672525825, "rouge1_precision": 0.12427774623745924, "rouge1_precision_stderr": 0.00396632764513016, "rouge1_recall": 0.31153733817117696, "rouge1_recall_stderr": 0.004862182707219614, "rouge2_fmeasure": 0.073579744703458, "rouge2_fmeasure_stderr": 0.0022399508108041687, "rouge2_precision": 0.061122334555414014, "rouge2_precision_stderr": 0.0024752531890197427, "rouge2_recall": 0.1553537719896923, "rouge2_recall_stderr": 0.003521786839397489, "rougeL_fmeasure": 0.1343719484645983, "rougeL_fmeasure_stderr": 0.0029138401067494405, "rougeL_precision": 0.10862059194070799, "rougeL_precision_stderr": 0.0032794570812240747, "rougeL_recall": 0.2880040612685418, "rougeL_recall_stderr": 0.004452369074617207, "rougeLsum_fmeasure": 0.13751466322243355, "rougeLsum_fmeasure_stderr": 0.0030168231727520462, "rougeLsum_precision": 0.11186894190492254, "rougeLsum_precision_stderr": 0.0034133834955339783, "rougeLsum_recall": 0.2921099418130985, "rougeLsum_recall_stderr": 0.0044981987732144475}}, "3": {"PALM_prompt": {"bleu": 0.6005511019489902, "bleu_stderr": 0.03451530801039688, "rouge1_fmeasure": 0.16481776831623232, "rouge1_fmeasure_stderr": 0.0038682235238341116, "rouge1_precision": 0.13595589597527172, "rouge1_precision_stderr": 0.004222986885593746, "rouge1_recall": 0.33095418350217154, "rouge1_recall_stderr": 0.0051126113252587, "rouge2_fmeasure": 0.08281371490457289, "rouge2_fmeasure_stderr": 0.002614718922183248, "rouge2_precision": 0.06960048861029224, "rouge2_precision_stderr": 0.0027985379538191905, "rouge2_recall": 0.16775824178008983, "rouge2_recall_stderr": 0.0037608840409452783, "rougeL_fmeasure": 0.1462708825192011, "rougeL_fmeasure_stderr": 0.0032850506015328065, "rougeL_precision": 0.11879183737182318, "rougeL_precision_stderr": 0.003583977041097007, "rougeL_recall": 0.30406006315984274, "rougeL_recall_stderr": 0.004643180781154661, "rougeLsum_fmeasure": 0.14946371142957862, "rougeLsum_fmeasure_stderr": 0.0033711111276765737, "rougeLsum_precision": 0.12214153222625562, "rougeLsum_precision_stderr": 0.0037097941549426336, "rougeLsum_recall": 0.3076377720124529, "rougeLsum_recall_stderr": 0.0046729883356302375}}, "4": {"PALM_prompt": {"bleu": 0.6245188789842254, "bleu_stderr": 0.043490522758658445, "rouge1_fmeasure": 0.17222603573029266, "rouge1_fmeasure_stderr": 0.003921731867593103, "rouge1_precision": 0.14786580825593648, "rouge1_precision_stderr": 0.004627492119408001, "rouge1_recall": 0.3383750446597362, "rouge1_recall_stderr": 0.004749410285992037, "rouge2_fmeasure": 0.08713860881109199, "rouge2_fmeasure_stderr": 0.002642546281127278, "rouge2_precision": 0.07698153502052321, "rouge2_precision_stderr": 0.0031209348406096736, "rouge2_recall": 0.1718812686921174, "rouge2_recall_stderr": 0.003529827492808453, "rougeL_fmeasure": 0.15325650518011516, "rougeL_fmeasure_stderr": 0.0033232600369196875, "rougeL_precision": 0.1294373882259293, "rougeL_precision_stderr": 0.003923291361672725, "rougeL_recall": 0.31167522711756507, "rougeL_recall_stderr": 0.00437544273005526, "rougeLsum_fmeasure": 0.15679817099191065, "rougeLsum_fmeasure_stderr": 0.003436174687018384, "rougeLsum_precision": 0.13331179138633883, "rougeLsum_precision_stderr": 0.004083238268648474, "rougeLsum_recall": 0.3154382483492274, "rougeLsum_recall_stderr": 0.0043923097345808845}}, "5": {"PALM_prompt": {"bleu": 0.690349543623733, "bleu_stderr": 0.037462509241486704, "rouge1_fmeasure": 0.18047036475829212, "rouge1_fmeasure_stderr": 0.004008854616724969, "rouge1_precision": 0.15622015160603553, "rouge1_precision_stderr": 0.004716488431001402, "rouge1_recall": 0.34792374373732987, "rouge1_recall_stderr": 0.004822507263881878, "rouge2_fmeasure": 0.0930691012178671, "rouge2_fmeasure_stderr": 0.0027170170506852424, "rouge2_precision": 0.08275177731282365, "rouge2_precision_stderr": 0.0031808930078121365, "rouge2_recall": 0.18065193154470569, "rouge2_recall_stderr": 0.003617404779594222, "rougeL_fmeasure": 0.15947807280240164, "rougeL_fmeasure_stderr": 0.00339577303947939, "rougeL_precision": 0.13603046372345778, "rougeL_precision_stderr": 0.004020369923896149, "rougeL_recall": 0.3181992629421937, "rougeL_recall_stderr": 0.00438340700122448, "rougeLsum_fmeasure": 0.16344169338350165, "rougeLsum_fmeasure_stderr": 0.0034931588485009957, "rougeLsum_precision": 0.14015533154496237, "rougeLsum_precision_stderr": 0.004159324286093359, "rougeLsum_recall": 0.3231216711299358, "rougeLsum_recall_stderr": 0.004412774889842664}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.7401292150366783, "bleu_stderr": 0.05870950000759347, "rouge1_fmeasure": 0.09262226734827564, "rouge1_fmeasure_stderr": 0.002438006555562961, "rouge1_precision": 0.10101653488556242, "rouge1_precision_stderr": 0.0032530374257675938, "rouge1_recall": 0.12382359005658215, "rouge1_recall_stderr": 0.003311350263072308, "rouge2_fmeasure": 0.023458200677554667, "rouge2_fmeasure_stderr": 0.0009269048009616802, "rouge2_precision": 0.021119629322483437, "rouge2_precision_stderr": 0.000867268036727509, "rouge2_recall": 0.03184028832690896, "rouge2_recall_stderr": 0.001315196256520591, "rougeL_fmeasure": 0.0717645545672235, "rougeL_fmeasure_stderr": 0.0018475862298041712, "rougeL_precision": 0.08164131674574245, "rougeL_precision_stderr": 0.002890373817028126, "rougeL_recall": 0.09744037722102081, "rougeL_recall_stderr": 0.002611244990111791, "rougeLsum_fmeasure": 0.08593512322791458, "rougeLsum_fmeasure_stderr": 0.0022685460052984064, "rougeLsum_precision": 0.09506262524089595, "rougeLsum_precision_stderr": 0.003153876364088973, "rougeLsum_recall": 0.11499957069726778, "rougeLsum_recall_stderr": 0.0030864345858981576}}, "1": {"tldr_en": {"bleu": 1.8195228421640262, "bleu_stderr": 0.08352209916798846, "rouge1_fmeasure": 0.15283090429353868, "rouge1_fmeasure_stderr": 0.0019824413317849196, "rouge1_precision": 0.2169406307055522, "rouge1_precision_stderr": 0.003725498619269963, "rouge1_recall": 0.1602777922005014, "rouge1_recall_stderr": 0.0023194868352840897, "rouge2_fmeasure": 0.030516647625530857, "rouge2_fmeasure_stderr": 0.0011026203736681755, "rouge2_precision": 0.05250080669816919, "rouge2_precision_stderr": 0.002263016873913571, "rouge2_recall": 0.029595318390725434, "rouge2_recall_stderr": 0.0011280692140449152, "rougeL_fmeasure": 0.12076719641202475, "rougeL_fmeasure_stderr": 0.0015785014789520583, "rougeL_precision": 0.17465569803991965, "rougeL_precision_stderr": 0.003198873475886084, "rougeL_recall": 0.1267991344776356, "rougeL_recall_stderr": 0.001844558639815861, "rougeLsum_fmeasure": 0.1443601231383759, "rougeLsum_fmeasure_stderr": 0.0018505558858251069, "rougeLsum_precision": 0.20508454330750828, "rougeLsum_precision_stderr": 0.0035353326008678463, "rougeLsum_recall": 0.1517146954188497, "rougeLsum_recall_stderr": 0.0021834314823700506}}, "2": {"tldr_en": {"bleu": 2.8890982233924274, "bleu_stderr": 0.07489960916470248, "rouge1_fmeasure": 0.2060405071459818, "rouge1_fmeasure_stderr": 0.002251177818368773, "rouge1_precision": 0.3400358202564136, "rouge1_precision_stderr": 0.004368456331414668, "rouge1_recall": 0.19549655317783554, "rouge1_recall_stderr": 0.0026239543642537643, "rouge2_fmeasure": 0.05659098002273207, "rouge2_fmeasure_stderr": 0.0013825154700548739, "rouge2_precision": 0.10414705512855632, "rouge2_precision_stderr": 0.0029764211051013624, "rouge2_recall": 0.052252858151520365, "rouge2_recall_stderr": 0.0013882181124994304, "rougeL_fmeasure": 0.1632339625235188, "rougeL_fmeasure_stderr": 0.0017925107334137358, "rougeL_precision": 0.2760810172165432, "rougeL_precision_stderr": 0.003817392548869396, "rougeL_recall": 0.15431925374992486, "rougeL_recall_stderr": 0.0020853728076912085, "rougeLsum_fmeasure": 0.19413584042277324, "rougeLsum_fmeasure_stderr": 0.0021219960169286357, "rougeLsum_precision": 0.32272701619444116, "rougeLsum_precision_stderr": 0.004237054067018847, "rougeLsum_recall": 0.18387985811231844, "rougeLsum_recall_stderr": 0.002467066081787791}}, "3": {"tldr_en": {"bleu": 1.890195824238381, "bleu_stderr": 0.07805309283654865, "rouge1_fmeasure": 0.17768534554173257, "rouge1_fmeasure_stderr": 0.002497324854394021, "rouge1_precision": 0.3143827035331544, "rouge1_precision_stderr": 0.004814681871436694, "rouge1_recall": 0.16312653314207656, "rouge1_recall_stderr": 0.0028028425609925864, "rouge2_fmeasure": 0.0510208899127158, "rouge2_fmeasure_stderr": 0.0014011608421103333, "rouge2_precision": 0.10012288852389835, "rouge2_precision_stderr": 0.0030408513717817094, "rouge2_recall": 0.04640858531424939, "rouge2_recall_stderr": 0.0014571215580260206, "rougeL_fmeasure": 0.14320515112174437, "rougeL_fmeasure_stderr": 0.0020306931695434237, "rougeL_precision": 0.25883690093372125, "rougeL_precision_stderr": 0.004162927984690604, "rougeL_recall": 0.13073894232805758, "rougeL_recall_stderr": 0.0022683935578694356, "rougeLsum_fmeasure": 0.16704762132090992, "rougeLsum_fmeasure_stderr": 0.002342688337895595, "rougeLsum_precision": 0.2982192683665052, "rougeLsum_precision_stderr": 0.004629601809394366, "rougeLsum_recall": 0.1526514018679153, "rougeLsum_recall_stderr": 0.0026042434071650534}}, "4": {"tldr_en": {"bleu": 0.016910620160853877, "bleu_stderr": 0.00364577886299514, "rouge1_fmeasure": 0.05712785595257542, "rouge1_fmeasure_stderr": 0.002109365575892117, "rouge1_precision": 0.10233714832400315, "rouge1_precision_stderr": 0.00387170332308452, "rouge1_recall": 0.052719560358311074, "rouge1_recall_stderr": 0.0021360645688620044, "rouge2_fmeasure": 0.015994832602106063, "rouge2_fmeasure_stderr": 0.0009271960700065752, "rouge2_precision": 0.03236639334422414, "rouge2_precision_stderr": 0.0020360160794573286, "rouge2_recall": 0.014676186959067014, "rouge2_recall_stderr": 0.000991238095490706, "rougeL_fmeasure": 0.0463830391676825, "rougeL_fmeasure_stderr": 0.001707583877770572, "rougeL_precision": 0.08539656258425662, "rougeL_precision_stderr": 0.003320722236518427, "rougeL_recall": 0.04253430518648541, "rougeL_recall_stderr": 0.0017210052280975444, "rougeLsum_fmeasure": 0.053156186981754575, "rougeLsum_fmeasure_stderr": 0.0019608311676159664, "rougeLsum_precision": 0.09625340675143208, "rougeLsum_precision_stderr": 0.0036657803196257096, "rougeLsum_recall": 0.048881870192824625, "rougeLsum_recall_stderr": 0.0019848013068469554}}, "5": {"tldr_en": {"bleu": 1.4571231589477147e-17, "bleu_stderr": 2.554040800257738e-15, "rouge1_fmeasure": 0.0091861211614601, "rouge1_fmeasure_stderr": 0.0008969173014851819, "rouge1_precision": 0.018095685011338746, "rouge1_precision_stderr": 0.00185447805960437, "rouge1_recall": 0.008607244652028168, "rouge1_recall_stderr": 0.0009194028038185624, "rouge2_fmeasure": 0.002725147355524338, "rouge2_fmeasure_stderr": 0.0004048462437499985, "rouge2_precision": 0.006014959811595776, "rouge2_precision_stderr": 0.0009805624350940475, "rouge2_recall": 0.0023894753339408787, "rouge2_recall_stderr": 0.0003776589361725097, "rougeL_fmeasure": 0.007656339590582189, "rougeL_fmeasure_stderr": 0.0007546272499233359, "rougeL_precision": 0.015576109016400224, "rougeL_precision_stderr": 0.001653922803893889, "rougeL_recall": 0.007132007829695769, "rougeL_recall_stderr": 0.0007575676626861256, "rougeLsum_fmeasure": 0.008689332392498271, "rougeLsum_fmeasure_stderr": 0.000852751466212803, "rougeLsum_precision": 0.01720829814617215, "rougeLsum_precision_stderr": 0.001777168147572916, "rougeLsum_recall": 0.00818345077420238, "rougeLsum_recall_stderr": 0.000884640095931326}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.8176691711249537, "bleu_stderr": 0.05995542560680462, "rouge1_fmeasure": 0.12962478833198351, "rouge1_fmeasure_stderr": 0.0026733541462707695, "rouge1_precision": 0.11995524671016493, "rouge1_precision_stderr": 0.002674303424141786, "rouge1_recall": 0.15915193434349853, "rouge1_recall_stderr": 0.0032972190406054414, "rouge2_fmeasure": 0.03603975902395983, "rouge2_fmeasure_stderr": 0.0012403288414746835, "rouge2_precision": 0.03280986461326413, "rouge2_precision_stderr": 0.0011206239984645086, "rouge2_recall": 0.04550105277967982, "rouge2_recall_stderr": 0.0016902484384178876, "rougeL_fmeasure": 0.10376435983061806, "rougeL_fmeasure_stderr": 0.0019651761643805117, "rougeL_precision": 0.09452651957178927, "rougeL_precision_stderr": 0.0018963480115027633, "rougeL_recall": 0.12988017210774444, "rougeL_recall_stderr": 0.0025557466013964663, "rougeLsum_fmeasure": 0.11626650837633533, "rougeLsum_fmeasure_stderr": 0.002446339204031, "rougeLsum_precision": 0.10794550532453419, "rougeLsum_precision_stderr": 0.002439267929763401, "rougeLsum_recall": 0.14233639462065437, "rougeLsum_recall_stderr": 0.00302666138111876}}, "1": {"generate_text_restaurant": {"bleu": 11.849671487305415, "bleu_stderr": 0.1360222064360011, "rouge1_fmeasure": 0.45449662451133166, "rouge1_fmeasure_stderr": 0.002333690577738812, "rouge1_precision": 0.54188605893543, "rouge1_precision_stderr": 0.003246758820446708, "rouge1_recall": 0.4314024243954027, "rouge1_recall_stderr": 0.0029616850251012895, "rouge2_fmeasure": 0.2121926766511087, "rouge2_fmeasure_stderr": 0.0020146533728953066, "rouge2_precision": 0.2562791831846635, "rouge2_precision_stderr": 0.002639527749513042, "rouge2_recall": 0.20134452678189727, "rouge2_recall_stderr": 0.0021665892377752327, "rougeL_fmeasure": 0.3309578358109194, "rougeL_fmeasure_stderr": 0.002047514034389017, "rougeL_precision": 0.3968055602906763, "rougeL_precision_stderr": 0.002884957533719286, "rougeL_recall": 0.3135108993655708, "rougeL_recall_stderr": 0.002421217906260913, "rougeLsum_fmeasure": 0.3729160698976979, "rougeLsum_fmeasure_stderr": 0.002328237682996928, "rougeLsum_precision": 0.44543454886093686, "rougeLsum_precision_stderr": 0.003160000527797213, "rougeLsum_recall": 0.3537585371537755, "rougeLsum_recall_stderr": 0.0027469285035271475}}, "2": {"generate_text_restaurant": {"bleu": 14.500866321633556, "bleu_stderr": 0.21652939369858226, "rouge1_fmeasure": 0.4837551797964578, "rouge1_fmeasure_stderr": 0.0022147223749886054, "rouge1_precision": 0.5577858917634193, "rouge1_precision_stderr": 0.003247785025897439, "rouge1_recall": 0.4675413035402858, "rouge1_recall_stderr": 0.002820078928761888, "rouge2_fmeasure": 0.23945439459321566, "rouge2_fmeasure_stderr": 0.002051628654300672, "rouge2_precision": 0.27932023326938354, "rouge2_precision_stderr": 0.0026973630619244273, "rouge2_recall": 0.23167147979272804, "rouge2_recall_stderr": 0.0022172627136572156, "rougeL_fmeasure": 0.3598482761759142, "rougeL_fmeasure_stderr": 0.0020447863689909054, "rougeL_precision": 0.41572829682147167, "rougeL_precision_stderr": 0.0029006552995420294, "rougeL_recall": 0.3478030944709029, "rougeL_recall_stderr": 0.002413752959029049, "rougeLsum_fmeasure": 0.4056412361905643, "rougeLsum_fmeasure_stderr": 0.0022938418811786596, "rougeLsum_precision": 0.4676801531783358, "rougeLsum_precision_stderr": 0.0031627544428160766, "rougeLsum_recall": 0.39184282368555173, "rougeLsum_recall_stderr": 0.002694948881819574}}, "3": {"generate_text_restaurant": {"bleu": 14.99356088381018, "bleu_stderr": 0.1939852688470928, "rouge1_fmeasure": 0.4885274020508225, "rouge1_fmeasure_stderr": 0.002197446931041306, "rouge1_precision": 0.560904943171157, "rouge1_precision_stderr": 0.003222339717903183, "rouge1_recall": 0.46948710399711374, "rouge1_recall_stderr": 0.0027577686714870798, "rouge2_fmeasure": 0.24528072211886423, "rouge2_fmeasure_stderr": 0.0021164271571705827, "rouge2_precision": 0.2844738744368861, "rouge2_precision_stderr": 0.002710055422490507, "rouge2_recall": 0.23612605197891567, "rouge2_recall_stderr": 0.0022922087007235313, "rougeL_fmeasure": 0.36547104984192025, "rougeL_fmeasure_stderr": 0.0020631564845025475, "rougeL_precision": 0.42065354031616564, "rougeL_precision_stderr": 0.0029044985788341323, "rougeL_recall": 0.351254841158613, "rougeL_recall_stderr": 0.0024156544408651705, "rougeLsum_fmeasure": 0.4121617578480254, "rougeLsum_fmeasure_stderr": 0.002317480403210135, "rougeLsum_precision": 0.473294687864865, "rougeLsum_precision_stderr": 0.0031673965755000533, "rougeLsum_recall": 0.39610686350311647, "rougeLsum_recall_stderr": 0.0026942679498965384}}, "4": {"generate_text_restaurant": {"bleu": 15.136408152402511, "bleu_stderr": 0.15749919205112253, "rouge1_fmeasure": 0.49008120449442055, "rouge1_fmeasure_stderr": 0.0021552779856922706, "rouge1_precision": 0.5635851478232797, "rouge1_precision_stderr": 0.003229028521004473, "rouge1_recall": 0.46904362683842155, "rouge1_recall_stderr": 0.002666498752628597, "rouge2_fmeasure": 0.2472610815193413, "rouge2_fmeasure_stderr": 0.002097203486030851, "rouge2_precision": 0.2877028860236848, "rouge2_precision_stderr": 0.0027336630161171856, "rouge2_recall": 0.23648543820909804, "rouge2_recall_stderr": 0.0022192023733188957, "rougeL_fmeasure": 0.3672468672821708, "rougeL_fmeasure_stderr": 0.0020504167271609996, "rougeL_precision": 0.4232377532809423, "rougeL_precision_stderr": 0.002905210399187484, "rougeL_recall": 0.3512864132211812, "rougeL_recall_stderr": 0.002353821229944638, "rougeLsum_fmeasure": 0.4139945135555939, "rougeLsum_fmeasure_stderr": 0.0022731887846098205, "rougeLsum_precision": 0.4758982382137059, "rougeLsum_precision_stderr": 0.003149472337396323, "rougeLsum_recall": 0.3964206507125601, "rougeLsum_recall_stderr": 0.0026288828261706028}}, "5": {"generate_text_restaurant": {"bleu": 14.94032761568535, "bleu_stderr": 0.16102163935491987, "rouge1_fmeasure": 0.4891066764513762, "rouge1_fmeasure_stderr": 0.002148432709098188, "rouge1_precision": 0.5647971657629298, "rouge1_precision_stderr": 0.0032050177663230373, "rouge1_recall": 0.46466204351732154, "rouge1_recall_stderr": 0.002636551188261336, "rouge2_fmeasure": 0.2475971300723347, "rouge2_fmeasure_stderr": 0.0020740967240209687, "rouge2_precision": 0.28959208448012996, "rouge2_precision_stderr": 0.002723369175901688, "rouge2_recall": 0.2349545016224875, "rouge2_recall_stderr": 0.0021871784713310173, "rougeL_fmeasure": 0.3676953770310896, "rougeL_fmeasure_stderr": 0.002043411505256857, "rougeL_precision": 0.4250552095964905, "rougeL_precision_stderr": 0.002889497509660382, "rougeL_recall": 0.3494271521246103, "rougeL_recall_stderr": 0.0023269838649924057, "rougeLsum_fmeasure": 0.41342063708708626, "rougeLsum_fmeasure_stderr": 0.002240351112078022, "rougeLsum_precision": 0.47747050984587586, "rougeLsum_precision_stderr": 0.0031407117559106392, "rougeLsum_recall": 0.3928622107079271, "rougeLsum_recall_stderr": 0.0025636957992988966}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.8631748315575967, "bleu_stderr": 0.06480985196854291, "rouge1_fmeasure": 0.19805083031043677, "rouge1_fmeasure_stderr": 0.0025145733920038504, "rouge1_precision": 0.14726644892868132, "rouge1_precision_stderr": 0.0024412028465323945, "rouge1_recall": 0.33236412764323403, "rouge1_recall_stderr": 0.004292159791327218, "rouge2_fmeasure": 0.045029580196435964, "rouge2_fmeasure_stderr": 0.0015159796252548507, "rouge2_precision": 0.03338148146365739, "rouge2_precision_stderr": 0.0014454654718671273, "rouge2_recall": 0.0775963205240964, "rouge2_recall_stderr": 0.002642772816149882, "rougeL_fmeasure": 0.150708876966239, "rougeL_fmeasure_stderr": 0.0019106881335396962, "rougeL_precision": 0.11274328349904972, "rougeL_precision_stderr": 0.0021403391288850487, "rougeL_recall": 0.253884590300403, "rougeL_recall_stderr": 0.0033701265161261294, "rougeLsum_fmeasure": 0.15690226758738812, "rougeLsum_fmeasure_stderr": 0.0021606792108516933, "rougeLsum_precision": 0.11711469488381401, "rougeLsum_precision_stderr": 0.0022541549353202995, "rougeLsum_recall": 0.26459055857012664, "rougeLsum_recall_stderr": 0.0037902287339387276}}, "1": {"article_DOC_summary": {"bleu": 2.002473681001451, "bleu_stderr": 0.10305039390700386, "rouge1_fmeasure": 0.21492593421689296, "rouge1_fmeasure_stderr": 0.0031040934015378273, "rouge1_precision": 0.201520198934412, "rouge1_precision_stderr": 0.0036780464289758986, "rouge1_recall": 0.28041072507766257, "rouge1_recall_stderr": 0.004470154542708083, "rouge2_fmeasure": 0.045086359683801695, "rouge2_fmeasure_stderr": 0.0019034075416325229, "rouge2_precision": 0.04262064763605291, "rouge2_precision_stderr": 0.0020875394875545616, "rouge2_recall": 0.059979799287456115, "rouge2_recall_stderr": 0.002459545390487186, "rougeL_fmeasure": 0.15921676436636747, "rougeL_fmeasure_stderr": 0.002420430590555424, "rougeL_precision": 0.15057288573196015, "rougeL_precision_stderr": 0.002929976392840731, "rougeL_recall": 0.20592545696933923, "rougeL_recall_stderr": 0.0033110515398117922, "rougeLsum_fmeasure": 0.16736923260398065, "rougeLsum_fmeasure_stderr": 0.0025093332042761462, "rougeLsum_precision": 0.15642146751721803, "rougeLsum_precision_stderr": 0.0029104557088062938, "rougeLsum_recall": 0.2199677896065397, "rougeLsum_recall_stderr": 0.0037276875782133504}}, "2": {"article_DOC_summary": {"bleu": 1.9767413966669858, "bleu_stderr": 0.12553384851261437, "rouge1_fmeasure": 0.21928064355323418, "rouge1_fmeasure_stderr": 0.0029906506411637493, "rouge1_precision": 0.2088093664550383, "rouge1_precision_stderr": 0.003591375397921926, "rouge1_recall": 0.28037833021310865, "rouge1_recall_stderr": 0.00418073064186992, "rouge2_fmeasure": 0.04498559646410484, "rouge2_fmeasure_stderr": 0.001797572147267301, "rouge2_precision": 0.04282030935093115, "rouge2_precision_stderr": 0.0018963252751686556, "rouge2_recall": 0.05836728040338388, "rouge2_recall_stderr": 0.0022732577336655444, "rougeL_fmeasure": 0.16195880232863943, "rougeL_fmeasure_stderr": 0.002341838899049842, "rougeL_precision": 0.15422100446453424, "rougeL_precision_stderr": 0.0027848170802648774, "rougeL_recall": 0.20777843317638175, "rougeL_recall_stderr": 0.0032512385248102136, "rougeLsum_fmeasure": 0.16811888843078998, "rougeLsum_fmeasure_stderr": 0.0024215692583980006, "rougeLsum_precision": 0.15873674200935498, "rougeLsum_precision_stderr": 0.0027827884387405604, "rougeLsum_recall": 0.21825435569219825, "rougeLsum_recall_stderr": 0.0035822959483663586}}, "3": {"article_DOC_summary": {"bleu": 2.0020914675362764, "bleu_stderr": 0.14545306393065818, "rouge1_fmeasure": 0.21363414740028736, "rouge1_fmeasure_stderr": 0.0033547861779570426, "rouge1_precision": 0.2040643001997412, "rouge1_precision_stderr": 0.003978248036078804, "rouge1_recall": 0.27307347161473916, "rouge1_recall_stderr": 0.004455443229628111, "rouge2_fmeasure": 0.044315357975490785, "rouge2_fmeasure_stderr": 0.0018794354037841253, "rouge2_precision": 0.0427132375189158, "rouge2_precision_stderr": 0.0020323931003614964, "rouge2_recall": 0.056734403722373934, "rouge2_recall_stderr": 0.0023427635867331836, "rougeL_fmeasure": 0.15848715345045697, "rougeL_fmeasure_stderr": 0.0026312535881803656, "rougeL_precision": 0.15146281632387826, "rougeL_precision_stderr": 0.0031018365348921524, "rougeL_recall": 0.20314923616617458, "rougeL_recall_stderr": 0.003479004056873755, "rougeLsum_fmeasure": 0.1642507173243999, "rougeLsum_fmeasure_stderr": 0.0026893440158164876, "rougeLsum_precision": 0.15567331452586086, "rougeLsum_precision_stderr": 0.0030921047823091897, "rougeLsum_recall": 0.21288484516878498, "rougeLsum_recall_stderr": 0.0037476662681603583}}, "4": {"article_DOC_summary": {"bleu": 0.3313737532545398, "bleu_stderr": 0.057620671081541584, "rouge1_fmeasure": 0.054580713604579945, "rouge1_fmeasure_stderr": 0.0032077855926012644, "rouge1_precision": 0.05845678560810508, "rouge1_precision_stderr": 0.003653372410391946, "rouge1_recall": 0.06546523451488562, "rouge1_recall_stderr": 0.00397320947448918, "rouge2_fmeasure": 0.010993328089942682, "rouge2_fmeasure_stderr": 0.0011929721928833114, "rouge2_precision": 0.011526059837135257, "rouge2_precision_stderr": 0.0014149014965583362, "rouge2_recall": 0.013070566192947936, "rouge2_recall_stderr": 0.0013385142420944767, "rougeL_fmeasure": 0.04045511548154733, "rougeL_fmeasure_stderr": 0.002398056707020803, "rougeL_precision": 0.044187543013943426, "rougeL_precision_stderr": 0.0028507649598664116, "rougeL_recall": 0.04837933471428071, "rougeL_recall_stderr": 0.0029701161810768185, "rougeLsum_fmeasure": 0.041976934818540805, "rougeLsum_fmeasure_stderr": 0.0024886979052922598, "rougeLsum_precision": 0.045470269077929414, "rougeLsum_precision_stderr": 0.002904632966614191, "rougeLsum_recall": 0.050635363980909044, "rougeLsum_recall_stderr": 0.0031412698278665725}}, "5": {"article_DOC_summary": {"bleu": 1.8341021693095957e-44, "bleu_stderr": 2.1637012594857334e-38, "rouge1_fmeasure": 0.001906885101987677, "rouge1_fmeasure_stderr": 0.0005780948322075463, "rouge1_precision": 0.0022940371923293613, "rouge1_precision_stderr": 0.0007143995060460097, "rouge1_recall": 0.0017348914893632757, "rouge1_recall_stderr": 0.0005253123299517621, "rouge2_fmeasure": 0.00010679337289617054, "rouge2_fmeasure_stderr": 7.591909328912052e-05, "rouge2_precision": 0.00011486155354079882, "rouge2_precision_stderr": 8.136503714231734e-05, "rouge2_recall": 0.00010005717552887364, "rouge2_recall_stderr": 7.143995839898157e-05, "rougeL_fmeasure": 0.001362800409731286, "rougeL_fmeasure_stderr": 0.0003965668916012721, "rougeL_precision": 0.0016335291518965692, "rougeL_precision_stderr": 0.0004934641653958932, "rougeL_recall": 0.001252059737745911, "rougeL_recall_stderr": 0.0003636768915155132, "rougeLsum_fmeasure": 0.001413249405796264, "rougeLsum_fmeasure_stderr": 0.0004059395809283557, "rougeLsum_precision": 0.0016839781479615478, "rougeLsum_precision_stderr": 0.0005010040710225287, "rougeLsum_recall": 0.0013025087338108892, "rougeLsum_recall_stderr": 0.0003738878391567918}}}}