Muennighoff's picture
Add
8393ff0
raw
history blame
4.7 kB
{"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.4960802864592442, "bleu_stderr": 0.021380837883074492, "rouge1_fmeasure": 0.14786213278861438, "rouge1_fmeasure_stderr": 0.0031938146599501016, "rouge1_precision": 0.12423888375310949, "rouge1_precision_stderr": 0.003927520234385026, "rouge1_recall": 0.3395421035752994, "rouge1_recall_stderr": 0.005780549518244501, "rouge2_fmeasure": 0.06912968892565469, "rouge2_fmeasure_stderr": 0.002043576415353945, "rouge2_precision": 0.057683820004525516, "rouge2_precision_stderr": 0.002468210498565516, "rouge2_recall": 0.16456769824088024, "rouge2_recall_stderr": 0.003743420405209025, "rougeL_fmeasure": 0.13281836968859598, "rougeL_fmeasure_stderr": 0.0027276505776339124, "rougeL_precision": 0.11191952410199484, "rougeL_precision_stderr": 0.003578978730657688, "rougeL_recall": 0.3121621335639146, "rougeL_recall_stderr": 0.0052383329376038635, "rougeLsum_fmeasure": 0.13567746858704577, "rougeLsum_fmeasure_stderr": 0.0028183733979661204, "rougeLsum_precision": 0.11451559924411767, "rougeLsum_precision_stderr": 0.0036504083069977523, "rougeLsum_recall": 0.31509582267608827, "rougeLsum_recall_stderr": 0.0052228503128477835}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 2.163921944532901, "bleu_stderr": 0.06020138914952586, "rouge1_fmeasure": 0.17078721260782917, "rouge1_fmeasure_stderr": 0.0020075735538509195, "rouge1_precision": 0.21882508075568352, "rouge1_precision_stderr": 0.003597920574166674, "rouge1_recall": 0.20280618509695303, "rouge1_recall_stderr": 0.00276729355224333, "rouge2_fmeasure": 0.035647619562210485, "rouge2_fmeasure_stderr": 0.0010681062524824736, "rouge2_precision": 0.05230670860263998, "rouge2_precision_stderr": 0.0020891409987626765, "rouge2_recall": 0.04220444882048039, "rouge2_recall_stderr": 0.0013638088609514993, "rougeL_fmeasure": 0.12999571959534578, "rougeL_fmeasure_stderr": 0.0014945625059261279, "rougeL_precision": 0.17128144890267422, "rougeL_precision_stderr": 0.0030628140903687377, "rougeL_recall": 0.15494801466132235, "rougeL_recall_stderr": 0.0021291826185906343, "rougeLsum_fmeasure": 0.16008115506528756, "rougeLsum_fmeasure_stderr": 0.0018693003571663728, "rougeLsum_precision": 0.2061319900646202, "rougeLsum_precision_stderr": 0.0034441292230208663, "rougeLsum_recall": 0.19030948880902482, "rougeLsum_recall_stderr": 0.002591161940397263}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 11.740965678849012, "bleu_stderr": 0.14535238897382605, "rouge1_fmeasure": 0.46610468504611824, "rouge1_fmeasure_stderr": 0.0023984674958165047, "rouge1_precision": 0.5606646645625755, "rouge1_precision_stderr": 0.00315496333575126, "rouge1_recall": 0.4385657317525879, "rouge1_recall_stderr": 0.003086147797612491, "rouge2_fmeasure": 0.21552261572642487, "rouge2_fmeasure_stderr": 0.0020237973202381545, "rouge2_precision": 0.26200194422669615, "rouge2_precision_stderr": 0.0025681274288702092, "rouge2_recall": 0.20301251625980535, "rouge2_recall_stderr": 0.0021895115852467433, "rougeL_fmeasure": 0.3326980951439758, "rougeL_fmeasure_stderr": 0.002035801332390331, "rougeL_precision": 0.4032769084137222, "rougeL_precision_stderr": 0.002814330839467536, "rougeL_recall": 0.31215805913323763, "rougeL_recall_stderr": 0.0024443897751257075, "rougeLsum_fmeasure": 0.37464274686721416, "rougeLsum_fmeasure_stderr": 0.0023063938629818963, "rougeLsum_precision": 0.4521825868040406, "rougeLsum_precision_stderr": 0.003046569469118969, "rougeLsum_recall": 0.3519436291443431, "rougeLsum_recall_stderr": 0.002762194235759685}}, "gem_xsum": {"article_DOC_summary": {"bleu": 0.583222650214418, "bleu_stderr": 0.07975217211736225, "rouge1_fmeasure": 0.13555413684909157, "rouge1_fmeasure_stderr": 0.002125612750711737, "rouge1_precision": 0.1178644660030508, "rouge1_precision_stderr": 0.00219096287290822, "rouge1_recall": 0.1924934035938564, "rouge1_recall_stderr": 0.0033225181486726666, "rouge2_fmeasure": 0.012493056687956312, "rouge2_fmeasure_stderr": 0.0008578763694659354, "rouge2_precision": 0.01069442154631991, "rouge2_precision_stderr": 0.000831022276397956, "rouge2_recall": 0.018653409592597543, "rouge2_recall_stderr": 0.0012441071234174312, "rougeL_fmeasure": 0.10720639352315421, "rougeL_fmeasure_stderr": 0.001610346697901536, "rougeL_precision": 0.09295708404480672, "rougeL_precision_stderr": 0.0016476646687891814, "rougeL_recall": 0.1534133785811412, "rougeL_recall_stderr": 0.0026375797405556313, "rougeLsum_fmeasure": 0.10802611481419844, "rougeLsum_fmeasure_stderr": 0.0016693167068583155, "rougeLsum_precision": 0.09355588459952982, "rougeLsum_precision_stderr": 0.001676060001476819, "rougeLsum_recall": 0.15485290858414788, "rougeLsum_recall_stderr": 0.0027650897597436765}}}