task,metric,value,err,version anli_r1,acc,0.352,0.015110404505648664,0 anli_r2,acc,0.372,0.015292149942040577,0 anli_r3,acc,0.3258333333333333,0.013535422043417447,0 arc_challenge,acc,0.23378839590443687,0.01236822537850714,0 arc_challenge,acc_norm,0.24744027303754265,0.01261035266329267,0 arc_easy,acc,0.4553872053872054,0.01021886178761873,0 arc_easy,acc_norm,0.43602693602693604,0.010175459582759736,0 boolq,acc,0.4938837920489297,0.008744400681893475,1 cb,acc,0.5357142857142857,0.06724777654937658,1 cb,f1,0.37053140096618353,,1 copa,acc,0.65,0.047937248544110196,0 hellaswag,acc,0.3759211312487552,0.004833699243292346,0 hellaswag,acc_norm,0.44652459669388567,0.0049611615892284164,0 piqa,acc,0.6806311207834603,0.010877964076613735,0 piqa,acc_norm,0.6779107725788901,0.010902341695103438,0 rte,acc,0.5090252707581228,0.030091559826331334,0 sciq,acc,0.697,0.01453968371053524,0 sciq,acc_norm,0.692,0.01460648312734276,0 storycloze_2016,acc,0.6360235168359166,0.011126343044992838,0 winogrande,acc,0.5224940805051302,0.014038257824059874,0