| task,metric,value,err,version | |
| anli_r1,acc,0.338,0.014965960710224482,0 | |
| anli_r2,acc,0.341,0.014998131348402699,0 | |
| anli_r3,acc,0.3491666666666667,0.013767075395077249,0 | |
| arc_challenge,acc,0.3054607508532423,0.013460080478002501,0 | |
| arc_challenge,acc_norm,0.3267918088737201,0.013706665975587336,0 | |
| arc_easy,acc,0.6430976430976431,0.009830630210347005,0 | |
| arc_easy,acc_norm,0.5686026936026936,0.010162752847747505,0 | |
| boolq,acc,0.5972477064220183,0.008578054401368405,1 | |
| cb,acc,0.5,0.06741998624632421,1 | |
| cb,f1,0.33763440860215055,,1 | |
| copa,acc,0.76,0.04292346959909283,0 | |
| hellaswag,acc,0.4814777932682733,0.004986356526063966,0 | |
| hellaswag,acc_norm,0.6296554471220872,0.004819100456867812,0 | |
| piqa,acc,0.7415669205658324,0.010213971636773319,0 | |
| piqa,acc_norm,0.7421109902067464,0.010206956662056252,0 | |
| rte,acc,0.5884476534296029,0.029621832222417196,0 | |
| sciq,acc,0.869,0.010674874844837952,0 | |
| sciq,acc_norm,0.773,0.013253174964763921,0 | |
| storycloze_2016,acc,0.740780331373597,0.010133463176449564,0 | |
| winogrande,acc,0.611681136543015,0.01369745665845723,0 | |