| task,metric,value,err,version | |
| anli_r1,acc,0.348,0.015070604603768408,0 | |
| anli_r2,acc,0.355,0.01513949154378053,0 | |
| anli_r3,acc,0.3591666666666667,0.013855141559780354,0 | |
| arc_challenge,acc,0.27986348122866894,0.013119040897725922,0 | |
| arc_challenge,acc_norm,0.30716723549488056,0.013481034054980943,0 | |
| arc_easy,acc,0.6077441077441077,0.010018744689650043,0 | |
| arc_easy,acc_norm,0.6085858585858586,0.010014917532627817,0 | |
| boolq,acc,0.6162079510703364,0.008505584729104966,1 | |
| cb,acc,0.44642857142857145,0.06703189227942398,1 | |
| cb,f1,0.3114219114219114,,1 | |
| copa,acc,0.69,0.04648231987117316,0 | |
| hellaswag,acc,0.4095797649870544,0.00490751210312835,0 | |
| hellaswag,acc_norm,0.5337582154949213,0.004978395540514379,0 | |
| piqa,acc,0.7236126224156693,0.010434162388275615,0 | |
| piqa,acc_norm,0.7328618063112078,0.010323440492612423,0 | |
| rte,acc,0.49458483754512633,0.030094698123239966,0 | |
| sciq,acc,0.915,0.008823426366942324,0 | |
| sciq,acc_norm,0.918,0.00868051561552372,0 | |
| storycloze_2016,acc,0.6819882415820417,0.010769343495248544,0 | |
| winogrande,acc,0.5603788476716653,0.01394964977601569,0 | |