初始化项目，由ModelHub XC社区提供模型

Model: bigscience/bloomz-7b1-p3
Source: Original Platform

evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/merged.csv

@@ -0,0 +1,86 @@
+dataset,prompt,metric,value
+xcopa_id,C1 or C2? premise_idmt,accuracy,0.51
+xcopa_id,best_option_idmt,accuracy,0.53
+xcopa_id,cause_effect_idmt,accuracy,0.69
+xcopa_id,i_am_hesitating_idmt,accuracy,0.64
+xcopa_id,plausible_alternatives_idmt,accuracy,0.7
+xcopa_id,median,accuracy,0.64
+xcopa_sw,C1 or C2? premise_swmt,accuracy,0.6
+xcopa_sw,best_option_swmt,accuracy,0.62
+xcopa_sw,cause_effect_swmt,accuracy,0.49
+xcopa_sw,i_am_hesitating_swmt,accuracy,0.56
+xcopa_sw,plausible_alternatives_swmt,accuracy,0.54
+xcopa_sw,median,accuracy,0.56
+xcopa_ta,C1 or C2? premise_tamt,accuracy,0.52
+xcopa_ta,best_option_tamt,accuracy,0.55
+xcopa_ta,cause_effect_tamt,accuracy,0.63
+xcopa_ta,i_am_hesitating_tamt,accuracy,0.63
+xcopa_ta,plausible_alternatives_tamt,accuracy,0.66
+xcopa_ta,median,accuracy,0.63
+xcopa_vi,C1 or C2? premise_vimt,accuracy,0.55
+xcopa_vi,best_option_vimt,accuracy,0.61
+xcopa_vi,cause_effect_vimt,accuracy,0.64
+xcopa_vi,i_am_hesitating_vimt,accuracy,0.6
+xcopa_vi,plausible_alternatives_vimt,accuracy,0.64
+xcopa_vi,median,accuracy,0.61
+xcopa_zh,C1 or C2? premise_zhmt,accuracy,0.52
+xcopa_zh,best_option_zhmt,accuracy,0.61
+xcopa_zh,cause_effect_zhmt,accuracy,0.75
+xcopa_zh,i_am_hesitating_zhmt,accuracy,0.72
+xcopa_zh,plausible_alternatives_zhmt,accuracy,0.76
+xcopa_zh,median,accuracy,0.72
+xstory_cloze_ar,Answer Given options_armt,accuracy,0.7061548643282595
+xstory_cloze_ar,Choose Story Ending_armt,accuracy,0.786896095301125
+xstory_cloze_ar,Generate Ending_armt,accuracy,0.600926538716082
+xstory_cloze_ar,Novel Correct Ending_armt,accuracy,0.7511581733951026
+xstory_cloze_ar,Story Continuation and Options_armt,accuracy,0.757114493712773
+xstory_cloze_ar,median,accuracy,0.7511581733951026
+xstory_cloze_es,Answer Given options_esmt,accuracy,0.7902051621442753
+xstory_cloze_es,Choose Story Ending_esmt,accuracy,0.8160158835208471
+xstory_cloze_es,Generate Ending_esmt,accuracy,0.657180675049636
+xstory_cloze_es,Novel Correct Ending_esmt,accuracy,0.784910655195235
+xstory_cloze_es,Story Continuation and Options_esmt,accuracy,0.7696889477167439
+xstory_cloze_es,median,accuracy,0.784910655195235
+xstory_cloze_eu,Answer Given options_eumt,accuracy,0.6227663798808736
+xstory_cloze_eu,Choose Story Ending_eumt,accuracy,0.6763732627399074
+xstory_cloze_eu,Generate Ending_eumt,accuracy,0.5737921906022502
+xstory_cloze_eu,Novel Correct Ending_eumt,accuracy,0.686300463269358
+xstory_cloze_eu,Story Continuation and Options_eumt,accuracy,0.6637988087359364
+xstory_cloze_eu,median,accuracy,0.6637988087359364
+xstory_cloze_hi,Answer Given options_himt,accuracy,0.6697551290536069
+xstory_cloze_hi,Choose Story Ending_himt,accuracy,0.7160820648577101
+xstory_cloze_hi,Generate Ending_himt,accuracy,0.5923229649238915
+xstory_cloze_hi,Novel Correct Ending_himt,accuracy,0.6882859033752482
+xstory_cloze_hi,Story Continuation and Options_himt,accuracy,0.7048312375909993
+xstory_cloze_hi,median,accuracy,0.6882859033752482
+xstory_cloze_id,Answer Given options_idmt,accuracy,0.7346128391793514
+xstory_cloze_id,Choose Story Ending_idmt,accuracy,0.7511581733951026
+xstory_cloze_id,Generate Ending_idmt,accuracy,0.6201191264063534
+xstory_cloze_id,Novel Correct Ending_idmt,accuracy,0.728656518861681
+xstory_cloze_id,Story Continuation and Options_idmt,accuracy,0.7412309728656519
+xstory_cloze_id,median,accuracy,0.7346128391793514
+xstory_cloze_zh,Answer Given options_zhmt,accuracy,0.7425545996029119
+xstory_cloze_zh,Choose Story Ending_zhmt,accuracy,0.7941760423560555
+xstory_cloze_zh,Generate Ending_zhmt,accuracy,0.6247518199867638
+xstory_cloze_zh,Novel Correct Ending_zhmt,accuracy,0.7842488418266049
+xstory_cloze_zh,Story Continuation and Options_zhmt,accuracy,0.8034414295168762
+xstory_cloze_zh,median,accuracy,0.7842488418266049
+xwinograd_fr,Replace_frmt,accuracy,0.5180722891566265
+xwinograd_fr,True or False_frmt,accuracy,0.46987951807228917
+xwinograd_fr,does underscore refer to_frmt,accuracy,0.5421686746987951
+xwinograd_fr,stand for_frmt,accuracy,0.5060240963855421
+xwinograd_fr,underscore refer to_frmt,accuracy,0.5421686746987951
+xwinograd_fr,median,accuracy,0.5180722891566265
+xwinograd_pt,Replace_ptmt,accuracy,0.5057034220532319
+xwinograd_pt,True or False_ptmt,accuracy,0.5133079847908745
+xwinograd_pt,does underscore refer to_ptmt,accuracy,0.5209125475285171
+xwinograd_pt,stand for_ptmt,accuracy,0.5209125475285171
+xwinograd_pt,underscore refer to_ptmt,accuracy,0.49049429657794674
+xwinograd_pt,median,accuracy,0.5133079847908745
+xwinograd_zh,Replace_zhmt,accuracy,0.5238095238095238
+xwinograd_zh,True or False_zhmt,accuracy,0.5138888888888888
+xwinograd_zh,does underscore refer to_zhmt,accuracy,0.49404761904761907
+xwinograd_zh,stand for_zhmt,accuracy,0.49603174603174605
+xwinograd_zh,underscore refer to_zhmt,accuracy,0.503968253968254
+xwinograd_zh,median,accuracy,0.503968253968254
+multiple,average,multiple,0.6501688392588024