| task,metric,value,err,version | |
| anli_r1,acc,0.327,0.014842213153411242,0 | |
| anli_r2,acc,0.329,0.014865395385928359,0 | |
| anli_r3,acc,0.35083333333333333,0.013782212417178193,0 | |
| arc_challenge,acc,0.3302047781569966,0.013743085603760427,0 | |
| arc_challenge,acc_norm,0.3464163822525597,0.013905011180063246,0 | |
| arc_easy,acc,0.6662457912457912,0.009676065683575472,0 | |
| arc_easy,acc_norm,0.656986531986532,0.009740965666489234,0 | |
| boolq,acc,0.6204892966360857,0.00848734197575683,1 | |
| cb,acc,0.5714285714285714,0.06672848092813058,1 | |
| cb,f1,0.3985557884928954,,1 | |
| copa,acc,0.84,0.03684529491774709,0 | |
| hellaswag,acc,0.49422425811591314,0.004989448490164432,0 | |
| hellaswag,acc_norm,0.6600278828918542,0.004727312448892851,0 | |
| piqa,acc,0.7573449401523396,0.010002002569708698,0 | |
| piqa,acc_norm,0.7633297062023939,0.009916841655042809,0 | |
| rte,acc,0.5234657039711191,0.030063300411902652,0 | |
| sciq,acc,0.922,0.008484573530118585,0 | |
| sciq,acc_norm,0.922,0.008484573530118585,0 | |
| storycloze_2016,acc,0.7487974345269909,0.010029364281941636,0 | |
| winogrande,acc,0.6203630623520127,0.013639245403711156,0 | |