| task,metric,value,err,version | |
| anli_r1,acc,0.319,0.014746404865473487,0 | |
| anli_r2,acc,0.331,0.014888272588203931,0 | |
| anli_r3,acc,0.33666666666666667,0.013647602942406387,0 | |
| arc_challenge,acc,0.33361774744027306,0.013778687054176545,0 | |
| arc_challenge,acc_norm,0.34726962457337884,0.01391303452962044,0 | |
| arc_easy,acc,0.6923400673400674,0.009470292575831181,0 | |
| arc_easy,acc_norm,0.6531986531986532,0.009766326091716002,0 | |
| boolq,acc,0.637308868501529,0.008408838061823175,1 | |
| cb,acc,0.4107142857142857,0.0663363415035954,1 | |
| cb,f1,0.22313546423135466,,1 | |
| copa,acc,0.8,0.040201512610368445,0 | |
| hellaswag,acc,0.5329615614419438,0.004978927164792885,0 | |
| hellaswag,acc_norm,0.707329217287393,0.004540586983229989,0 | |
| piqa,acc,0.7834602829162133,0.009609984714384606,0 | |
| piqa,acc_norm,0.7878128400435256,0.009539299828174056,0 | |
| rte,acc,0.5090252707581228,0.030091559826331334,0 | |
| sciq,acc,0.929,0.008125578442487933,0 | |
| sciq,acc_norm,0.922,0.008484573530118588,0 | |
| storycloze_2016,acc,0.7562800641368252,0.009928097887358885,0 | |
| winogrande,acc,0.6227308602999211,0.013622567928799501,0 | |