| task,metric,value,err,version | |
| anli_r1,acc,0.33,0.014876872027456732,0 | |
| anli_r2,acc,0.34,0.014987482264363937,0 | |
| anli_r3,acc,0.35,0.013774667009018554,0 | |
| arc_challenge,acc,0.28071672354948807,0.01313123812697558,0 | |
| arc_challenge,acc_norm,0.30204778156996587,0.013417519144716417,0 | |
| arc_easy,acc,0.6165824915824916,0.009976995068264717,0 | |
| arc_easy,acc_norm,0.5917508417508418,0.010085566195791248,0 | |
| boolq,acc,0.5871559633027523,0.00861117243047287,1 | |
| cb,acc,0.375,0.06527912098338669,1 | |
| cb,f1,0.33730158730158727,,1 | |
| copa,acc,0.78,0.04163331998932261,0 | |
| hellaswag,acc,0.444035052778331,0.004958426152481896,0 | |
| hellaswag,acc_norm,0.58105954989046,0.004923772581848489,0 | |
| piqa,acc,0.73449401523395,0.010303308653024427,0 | |
| piqa,acc_norm,0.7372143634385201,0.010269354068140777,0 | |
| rte,acc,0.5342960288808665,0.030025579819366422,0 | |
| sciq,acc,0.883,0.010169287802713329,0 | |
| sciq,acc_norm,0.861,0.010945263761042967,0 | |
| storycloze_2016,acc,0.7103153393907001,0.01048980809194661,0 | |
| winogrande,acc,0.5864246250986582,0.013840971763195303,0 | |