| task,metric,value,err,version | |
| anli_r1,acc,0.33,0.014876872027456729,0 | |
| anli_r2,acc,0.329,0.014865395385928355,0 | |
| anli_r3,acc,0.33166666666666667,0.013596836729485171,0 | |
| arc_challenge,acc,0.32337883959044367,0.013669421630012129,0 | |
| arc_challenge,acc_norm,0.3199658703071672,0.013631345807016195,0 | |
| arc_easy,acc,0.6325757575757576,0.009892552616211555,0 | |
| arc_easy,acc_norm,0.617003367003367,0.00997492038453649,0 | |
| boolq,acc,0.6321100917431193,0.008434276591093021,1 | |
| cb,acc,0.19642857142857142,0.05357142857142859,1 | |
| cb,f1,0.19293024227234748,,1 | |
| copa,acc,0.76,0.04292346959909283,0 | |
| hellaswag,acc,0.4727145986855208,0.004982346155911131,0 | |
| hellaswag,acc_norm,0.6357299342760406,0.0048024139199326545,0 | |
| piqa,acc,0.7453754080522307,0.010164432237060489,0 | |
| piqa,acc_norm,0.7633297062023939,0.009916841655042809,0 | |
| rte,acc,0.5379061371841155,0.030009848912529113,0 | |
| sciq,acc,0.91,0.009054390204866439,0 | |
| sciq,acc_norm,0.898,0.009575368801653873,0 | |
| storycloze_2016,acc,0.7231427044361304,0.01034711289027693,0 | |
| winogrande,acc,0.5974743488555643,0.013782866831703044,0 | |