| task,metric,value,err,version | |
| anli_r1,acc,0.342,0.015008706182121731,0 | |
| anli_r2,acc,0.34,0.014987482264363937,0 | |
| anli_r3,acc,0.3491666666666667,0.013767075395077247,0 | |
| arc_challenge,acc,0.3054607508532423,0.013460080478002501,0 | |
| arc_challenge,acc_norm,0.33361774744027306,0.013778687054176546,0 | |
| arc_easy,acc,0.6435185185185185,0.009828046544504422,0 | |
| arc_easy,acc_norm,0.6165824915824916,0.009976995068264724,0 | |
| boolq,acc,0.6321100917431193,0.008434276591093028,1 | |
| cb,acc,0.42857142857142855,0.06672848092813058,1 | |
| cb,f1,0.36394984326018814,,1 | |
| copa,acc,0.8,0.040201512610368445,0 | |
| hellaswag,acc,0.47610037841067515,0.004984077906216097,0 | |
| hellaswag,acc_norm,0.6333399721171081,0.004809077205343497,0 | |
| piqa,acc,0.749183895538629,0.010113869547069044,0 | |
| piqa,acc_norm,0.7589771490750816,0.009979042717267312,0 | |
| rte,acc,0.49097472924187724,0.030091559826331334,0 | |
| sciq,acc,0.916,0.008776162089491123,0 | |
| sciq,acc_norm,0.905,0.0092769101031033,0 | |
| storycloze_2016,acc,0.721004810261892,0.010371620932652793,0 | |
| winogrande,acc,0.5895816890292028,0.013825107120035866,0 | |