| task,metric,value,err,version | |
| anli_r1,acc,0.347,0.015060472031706622,0 | |
| anli_r2,acc,0.361,0.015195720118175127,0 | |
| anli_r3,acc,0.34,0.013680495725767787,0 | |
| arc_challenge,acc,0.30119453924914674,0.01340674176784762,0 | |
| arc_challenge,acc_norm,0.3370307167235495,0.013813476652902269,0 | |
| arc_easy,acc,0.6283670033670034,0.009915897123658788,0 | |
| arc_easy,acc_norm,0.5972222222222222,0.010063960494989163,0 | |
| boolq,acc,0.5984709480122324,0.008573784490094754,1 | |
| cb,acc,0.375,0.06527912098338669,1 | |
| cb,f1,0.266719222178426,,1 | |
| copa,acc,0.82,0.038612291966536955,0 | |
| hellaswag,acc,0.47400916152160927,0.004983035420235718,0 | |
| hellaswag,acc_norm,0.6275642302330213,0.004824655406075563,0 | |
| piqa,acc,0.7546245919477693,0.010039831320422396,0 | |
| piqa,acc_norm,0.766050054406964,0.009877236895137446,0 | |
| rte,acc,0.4981949458483754,0.030096267148976626,0 | |
| sciq,acc,0.911,0.009008893392651518,0 | |
| sciq,acc_norm,0.898,0.009575368801653892,0 | |
| storycloze_2016,acc,0.7247461250668092,0.010328538400500567,0 | |
| winogrande,acc,0.584846093133386,0.013848684086658585,0 | |