Muennighoff's picture
Add scores
8263782
raw
history blame
3.3 kB
dataset,fewshots,prompt,metric,value
e2e_nlg_cleaned,0,generate_text_restaurant,rouge2_fmeasure,0.012769294373367771
e2e_nlg_cleaned,0,median,rouge2_fmeasure,0.012769294373367771
e2e_nlg_cleaned,1,generate_text_restaurant,rouge2_fmeasure,0.18427344702091913
e2e_nlg_cleaned,1,median,rouge2_fmeasure,0.18427344702091913
e2e_nlg_cleaned,2,generate_text_restaurant,rouge2_fmeasure,0.2101765831183815
e2e_nlg_cleaned,2,median,rouge2_fmeasure,0.2101765831183815
e2e_nlg_cleaned,3,generate_text_restaurant,rouge2_fmeasure,0.22103332973061124
e2e_nlg_cleaned,3,median,rouge2_fmeasure,0.22103332973061124
e2e_nlg_cleaned,4,generate_text_restaurant,rouge2_fmeasure,0.22268786623363584
e2e_nlg_cleaned,4,median,rouge2_fmeasure,0.22268786623363584
e2e_nlg_cleaned,5,generate_text_restaurant,rouge2_fmeasure,0.22475547301426657
e2e_nlg_cleaned,5,median,rouge2_fmeasure,0.22475547301426657
e2e_nlg_cleaned,5,average,multiple,0.17928266558186368
gem_xsum,0,article_DOC_summary,rouge2_fmeasure,0.04768368310993588
gem_xsum,0,median,rouge2_fmeasure,0.04768368310993588
gem_xsum,1,article_DOC_summary,rouge2_fmeasure,0.045112546772934525
gem_xsum,1,median,rouge2_fmeasure,0.045112546772934525
gem_xsum,2,article_DOC_summary,rouge2_fmeasure,0.04741261419771178
gem_xsum,2,median,rouge2_fmeasure,0.04741261419771178
gem_xsum,3,article_DOC_summary,rouge2_fmeasure,0.04579306632360622
gem_xsum,3,median,rouge2_fmeasure,0.04579306632360622
gem_xsum,4,article_DOC_summary,rouge2_fmeasure,0.014349999093671009
gem_xsum,4,median,rouge2_fmeasure,0.014349999093671009
gem_xsum,5,article_DOC_summary,rouge2_fmeasure,0.00046551069178623087
gem_xsum,5,median,rouge2_fmeasure,0.00046551069178623087
gem_xsum,5,average,multiple,0.03346957003160761
web_nlg_en,0,PALM_prompt,rouge2_fmeasure,0.04762017526127606
web_nlg_en,0,median,rouge2_fmeasure,0.04762017526127606
web_nlg_en,1,PALM_prompt,rouge2_fmeasure,0.05785803759738568
web_nlg_en,1,median,rouge2_fmeasure,0.05785803759738568
web_nlg_en,2,PALM_prompt,rouge2_fmeasure,0.05940509370992996
web_nlg_en,2,median,rouge2_fmeasure,0.05940509370992996
web_nlg_en,3,PALM_prompt,rouge2_fmeasure,0.06022531877051832
web_nlg_en,3,median,rouge2_fmeasure,0.06022531877051832
web_nlg_en,4,PALM_prompt,rouge2_fmeasure,0.06061578220428707
web_nlg_en,4,median,rouge2_fmeasure,0.06061578220428707
web_nlg_en,5,PALM_prompt,rouge2_fmeasure,0.0624035474416899
web_nlg_en,5,median,rouge2_fmeasure,0.0624035474416899
web_nlg_en,5,average,multiple,0.058021325830847834
wiki_lingua_en,0,tldr_en,rouge2_fmeasure,0.037091167992168994
wiki_lingua_en,0,median,rouge2_fmeasure,0.037091167992168994
wiki_lingua_en,1,tldr_en,rouge2_fmeasure,0.06328901574064953
wiki_lingua_en,1,median,rouge2_fmeasure,0.06328901574064953
wiki_lingua_en,2,tldr_en,rouge2_fmeasure,0.07067445283939051
wiki_lingua_en,2,median,rouge2_fmeasure,0.07067445283939051
wiki_lingua_en,3,tldr_en,rouge2_fmeasure,0.0583824000959267
wiki_lingua_en,3,median,rouge2_fmeasure,0.0583824000959267
wiki_lingua_en,4,tldr_en,rouge2_fmeasure,0.018412425374697422
wiki_lingua_en,4,median,rouge2_fmeasure,0.018412425374697422
wiki_lingua_en,5,tldr_en,rouge2_fmeasure,0.002970906530619929
wiki_lingua_en,5,median,rouge2_fmeasure,0.002970906530619929
wiki_lingua_en,5,average,multiple,0.04180339476224218