| task,metric,value,err,version | |
| anli_r1,acc,0.315,0.0146966319607925,0 | |
| anli_r2,acc,0.345,0.015039986742055237,0 | |
| anli_r3,acc,0.3175,0.013443538681348054,0 | |
| arc_challenge,acc,0.30204778156996587,0.01341751914471642,0 | |
| arc_challenge,acc_norm,0.3242320819112628,0.01367881039951882,0 | |
| arc_easy,acc,0.6174242424242424,0.009972837790531477,0 | |
| arc_easy,acc_norm,0.5942760942760943,0.01007575554012888,0 | |
| boolq,acc,0.6339449541284403,0.008425419107728748,1 | |
| cb,acc,0.17857142857142858,0.05164277182008721,1 | |
| cb,f1,0.16728395061728393,,1 | |
| copa,acc,0.81,0.03942772444036623,0 | |
| hellaswag,acc,0.4751045608444533,0.004983592410934173,0 | |
| hellaswag,acc_norm,0.6286596295558654,0.004821757734156732,0 | |
| piqa,acc,0.749727965179543,0.010106561880089782,0 | |
| piqa,acc_norm,0.7568008705114254,0.010009611953858922,0 | |
| rte,acc,0.4981949458483754,0.030096267148976633,0 | |
| sciq,acc,0.903,0.00936368937324811,0 | |
| sciq,acc_norm,0.88,0.010281328012747386,0 | |
| storycloze_2016,acc,0.7188669160876536,0.010395836091628112,0 | |
| winogrande,acc,0.5927387529597474,0.013808654122417845,0 | |