| task,metric,value,err,version | |
| anli_r1,acc,0.32,0.014758652303574876,0 | |
| anli_r2,acc,0.367,0.015249378464171754,0 | |
| anli_r3,acc,0.31916666666666665,0.01346230971200513,0 | |
| arc_challenge,acc,0.2363481228668942,0.012414960524301823,0 | |
| arc_challenge,acc_norm,0.26791808873720135,0.012942030195136421,0 | |
| arc_easy,acc,0.5366161616161617,0.010232235063933028,0 | |
| arc_easy,acc_norm,0.5180976430976431,0.010253060653479168,0 | |
| boolq,acc,0.518348623853211,0.008739164562341832,1 | |
| cb,acc,0.42857142857142855,0.06672848092813058,1 | |
| cb,f1,0.30151946818613484,,1 | |
| copa,acc,0.72,0.04512608598542127,0 | |
| hellaswag,acc,0.3540131447918741,0.004772358395130448,0 | |
| hellaswag,acc_norm,0.4362676757618004,0.004949080334816027,0 | |
| piqa,acc,0.6926006528835691,0.01076560250693907,0 | |
| piqa,acc_norm,0.6936887921653971,0.010754970032367323,0 | |
| rte,acc,0.44404332129963897,0.029907396333795983,0 | |
| sciq,acc,0.895,0.009698921026024966,0 | |
| sciq,acc_norm,0.879,0.010318210380946097,0 | |
| storycloze_2016,acc,0.6290753607696419,0.011170519624693485,0 | |
| winogrande,acc,0.5209155485398579,0.014040185494212949,0 | |