| task,metric,value,err,version | |
| anli_r1,acc,0.325,0.014818724459095526,0 | |
| anli_r2,acc,0.329,0.014865395385928367,0 | |
| anli_r3,acc,0.3325,0.013605417345710528,0 | |
| arc_challenge,acc,0.28668941979522183,0.01321498632927478,0 | |
| arc_challenge,acc_norm,0.2986348122866894,0.01337407861506875,0 | |
| arc_easy,acc,0.6039562289562289,0.010035580962097944,0 | |
| arc_easy,acc_norm,0.5429292929292929,0.01022189756425604,0 | |
| boolq,acc,0.591131498470948,0.008598573693259113,1 | |
| cb,acc,0.48214285714285715,0.0673769750864465,1 | |
| cb,f1,0.3156716417910448,,1 | |
| copa,acc,0.77,0.04229525846816506,0 | |
| hellaswag,acc,0.476000796654053,0.00498403025050729,0 | |
| hellaswag,acc_norm,0.6229834694284008,0.004836486437527274,0 | |
| piqa,acc,0.749183895538629,0.010113869547069044,0 | |
| piqa,acc_norm,0.7682263329706203,0.009845143772794046,0 | |
| rte,acc,0.555956678700361,0.029907396333795987,0 | |
| sciq,acc,0.857,0.01107581480856704,0 | |
| sciq,acc_norm,0.764,0.013434451402438676,0 | |
| storycloze_2016,acc,0.7172634954569749,0.01041380648612127,0 | |
| winogrande,acc,0.5880031570639306,0.013833112857645938,0 | |