| task,metric,value,err,version | |
| anli_r1,acc,0.36,0.015186527932040126,0 | |
| anli_r2,acc,0.368,0.015258073561521802,0 | |
| anli_r3,acc,0.335,0.013630871843821474,0 | |
| arc_challenge,acc,0.302901023890785,0.013428241573185349,0 | |
| arc_challenge,acc_norm,0.3199658703071672,0.013631345807016193,0 | |
| arc_easy,acc,0.6233164983164983,0.009942848077476172,0 | |
| arc_easy,acc_norm,0.6220538720538721,0.009949405744045481,0 | |
| boolq,acc,0.6079510703363914,0.008538802914911995,1 | |
| cb,acc,0.5,0.06741998624632421,1 | |
| cb,f1,0.2222222222222222,,1 | |
| copa,acc,0.8,0.040201512610368445,0 | |
| hellaswag,acc,0.4727145986855208,0.004982346155911132,0 | |
| hellaswag,acc_norm,0.6279625572595101,0.004823604775015894,0 | |
| piqa,acc,0.749727965179543,0.01010656188008979,0 | |
| piqa,acc_norm,0.7546245919477693,0.010039831320422384,0 | |
| rte,acc,0.5342960288808665,0.030025579819366426,0 | |
| sciq,acc,0.912,0.008963053962592085,0 | |
| sciq,acc_norm,0.905,0.0092769101031033,0 | |
| storycloze_2016,acc,0.7220737573490112,0.010359403651225865,0 | |
| winogrande,acc,0.5895816890292028,0.01382510712003587,0 | |