| task,metric,value,err,version | |
| anli_r1,acc,0.333,0.014910846164229868,0 | |
| anli_r2,acc,0.336,0.014944140233795027,0 | |
| anli_r3,acc,0.3433333333333333,0.01371263383046586,0 | |
| arc_challenge,acc,0.2619453924914676,0.012849054826858114,0 | |
| arc_challenge,acc_norm,0.295221843003413,0.01332975029338232,0 | |
| arc_easy,acc,0.569023569023569,0.010161552863493758,0 | |
| arc_easy,acc_norm,0.5071548821548821,0.01025873302244637,0 | |
| boolq,acc,0.617737003058104,0.008499149690449282,1 | |
| cb,acc,0.42857142857142855,0.06672848092813058,1 | |
| cb,f1,0.21956970232832299,,1 | |
| copa,acc,0.79,0.040936018074033256,0 | |
| hellaswag,acc,0.4629555865365465,0.0049760677264325615,0 | |
| hellaswag,acc_norm,0.6056562437761402,0.004877104939356237,0 | |
| piqa,acc,0.7442872687704026,0.010178690109459857,0 | |
| piqa,acc_norm,0.7475516866158868,0.010135665547362354,0 | |
| rte,acc,0.5848375451263538,0.02966006629089349,0 | |
| sciq,acc,0.83,0.01188449583454167,0 | |
| sciq,acc_norm,0.734,0.013979965645145158,0 | |
| storycloze_2016,acc,0.7097808658471406,0.010495529690730063,0 | |
| winogrande,acc,0.5832675611681136,0.01385625007279632,0 | |