| task,metric,value,err,version | |
| anli_r1,acc,0.335,0.014933117490932575,0 | |
| anli_r2,acc,0.337,0.014955087918653605,0 | |
| anli_r3,acc,0.33916666666666667,0.013672343491681819,0 | |
| arc_challenge,acc,0.2738907849829352,0.013032004972989501,0 | |
| arc_challenge,acc_norm,0.2935153583617747,0.013307250444941117,0 | |
| arc_easy,acc,0.6069023569023569,0.010022540618945312,0 | |
| arc_easy,acc_norm,0.5526094276094277,0.01020283238541565,0 | |
| boolq,acc,0.5642201834862385,0.00867262173201595,1 | |
| cb,acc,0.4107142857142857,0.0663363415035954,1 | |
| cb,f1,0.1940928270042194,,1 | |
| copa,acc,0.77,0.04229525846816506,0 | |
| hellaswag,acc,0.44911372236606256,0.004963872936857941,0 | |
| hellaswag,acc_norm,0.5824536944831706,0.004921466591335056,0 | |
| piqa,acc,0.7421109902067464,0.010206956662056262,0 | |
| piqa,acc_norm,0.7470076169749728,0.010142888698862455,0 | |
| rte,acc,0.5812274368231047,0.02969666108123482,0 | |
| sciq,acc,0.869,0.010674874844837952,0 | |
| sciq,acc_norm,0.797,0.012726073744598285,0 | |
| storycloze_2016,acc,0.7071084981293426,0.010523873293246305,0 | |
| winogrande,acc,0.5698500394632992,0.013914685094716694,0 | |