| task,metric,value,err,version | |
| anli_r1,acc,0.318,0.014734079309311901,0 | |
| anli_r2,acc,0.347,0.015060472031706618,0 | |
| anli_r3,acc,0.3275,0.013553211167251953,0 | |
| arc_challenge,acc,0.30716723549488056,0.013481034054980945,0 | |
| arc_challenge,acc_norm,0.33276450511945393,0.013769863046192314,0 | |
| arc_easy,acc,0.6254208754208754,0.00993175882041061,0 | |
| arc_easy,acc_norm,0.5993265993265994,0.010055304474255585,0 | |
| boolq,acc,0.636697247706422,0.008411885836787163,1 | |
| cb,acc,0.35714285714285715,0.0646095738380922,1 | |
| cb,f1,0.26868521549372615,,1 | |
| copa,acc,0.79,0.040936018074033256,0 | |
| hellaswag,acc,0.47470623381796456,0.004983392650570956,0 | |
| hellaswag,acc_norm,0.6330412268472416,0.004809901151234834,0 | |
| piqa,acc,0.749727965179543,0.010106561880089786,0 | |
| piqa,acc_norm,0.76550598476605,0.00988520314324054,0 | |
| rte,acc,0.51985559566787,0.030072723167317184,0 | |
| sciq,acc,0.904,0.009320454434783222,0 | |
| sciq,acc_norm,0.893,0.009779910359847165,0 | |
| storycloze_2016,acc,0.7188669160876536,0.010395836091628113,0 | |
| winogrande,acc,0.5816890292028414,0.013863669961195918,0 | |