| task,metric,value,err,version | |
| anli_r1,acc,0.289,0.014341711358296191,0 | |
| anli_r2,acc,0.352,0.015110404505648666,0 | |
| anli_r3,acc,0.335,0.013630871843821474,0 | |
| arc_challenge,acc,0.23122866894197952,0.012320858834772276,0 | |
| arc_challenge,acc_norm,0.26791808873720135,0.012942030195136432,0 | |
| arc_easy,acc,0.5332491582491582,0.010237073872130744,0 | |
| arc_easy,acc_norm,0.5227272727272727,0.010249179090605987,0 | |
| boolq,acc,0.5382262996941896,0.00871946009810685,1 | |
| cb,acc,0.5,0.06741998624632421,1 | |
| cb,f1,0.35047619047619044,,1 | |
| copa,acc,0.68,0.04688261722621504,0 | |
| hellaswag,acc,0.36247759410476,0.004797332565990064,0 | |
| hellaswag,acc_norm,0.44911372236606256,0.0049638729368579396,0 | |
| piqa,acc,0.6985854189336235,0.010706248242753761,0 | |
| piqa,acc_norm,0.6942328618063112,0.010749627366141642,0 | |
| rte,acc,0.5415162454873647,0.029992535385373314,0 | |
| sciq,acc,0.891,0.009859828407037186,0 | |
| sciq,acc_norm,0.882,0.010206869264381791,0 | |
| storycloze_2016,acc,0.6392303580972741,0.011105110530046357,0 | |
| winogrande,acc,0.5138121546961326,0.01404712291644041,0 | |