| task,metric,value,err,version | |
| anli_r1,acc,0.321,0.014770821817934642,0 | |
| anli_r2,acc,0.321,0.014770821817934647,0 | |
| anli_r3,acc,0.3333333333333333,0.013613950010225603,0 | |
| arc_challenge,acc,0.28668941979522183,0.013214986329274762,0 | |
| arc_challenge,acc_norm,0.3037542662116041,0.013438909184778759,0 | |
| arc_easy,acc,0.6043771043771043,0.010033741393430986,0 | |
| arc_easy,acc_norm,0.5686026936026936,0.010162752847747501,0 | |
| boolq,acc,0.5773700305810398,0.008639722698719023,1 | |
| cb,acc,0.5,0.06741998624632421,1 | |
| cb,f1,0.35714285714285704,,1 | |
| copa,acc,0.74,0.04408440022768079,0 | |
| hellaswag,acc,0.4691296554471221,0.004980262025472478,0 | |
| hellaswag,acc_norm,0.6161123282214698,0.004853371646239242,0 | |
| piqa,acc,0.7519042437431991,0.010077118315574715,0 | |
| piqa,acc_norm,0.7606093579978237,0.00995588425029168,0 | |
| rte,acc,0.5667870036101083,0.02982676408213828,0 | |
| sciq,acc,0.883,0.010169287802713329,0 | |
| sciq,acc_norm,0.859,0.011010914595992445,0 | |
| storycloze_2016,acc,0.721004810261892,0.010371620932652793,0 | |
| winogrande,acc,0.5651144435674822,0.013932814110418025,0 | |