| task,metric,value,err,version | |
| anli_r1,acc,0.31,0.014632638658632902,0 | |
| anli_r2,acc,0.345,0.015039986742055238,0 | |
| anli_r3,acc,0.31916666666666665,0.013462309712005136,0 | |
| arc_challenge,acc,0.30119453924914674,0.013406741767847626,0 | |
| arc_challenge,acc_norm,0.3191126279863481,0.013621696119173307,0 | |
| arc_easy,acc,0.6464646464646465,0.00980972894815149,0 | |
| arc_easy,acc_norm,0.6212121212121212,0.009953737656542042,0 | |
| boolq,acc,0.5837920489296636,0.008621380519419276,1 | |
| cb,acc,0.375,0.06527912098338669,1 | |
| cb,f1,0.26053639846743293,,1 | |
| copa,acc,0.8,0.040201512610368445,0 | |
| hellaswag,acc,0.4486158135829516,0.004963362085275558,0 | |
| hellaswag,acc_norm,0.59061939852619,0.004907146229347537,0 | |
| piqa,acc,0.7247007616974973,0.01042142927736953,0 | |
| piqa,acc_norm,0.719260065288357,0.010484325438311827,0 | |
| rte,acc,0.5054151624548736,0.03009469812323996,0 | |
| sciq,acc,0.872,0.010570133761108665,0 | |
| sciq,acc_norm,0.855,0.01113997751789013,0 | |
| storycloze_2016,acc,0.6846606092998396,0.01074498911626067,0 | |
| winogrande,acc,0.5880031570639306,0.013833112857645935,0 | |