| task,metric,value,err,version | |
| anli_r1,acc,0.342,0.015008706182121733,0 | |
| anli_r2,acc,0.331,0.014888272588203943,0 | |
| anli_r3,acc,0.3233333333333333,0.013508372867300226,0 | |
| arc_challenge,acc,0.295221843003413,0.013329750293382318,0 | |
| arc_challenge,acc_norm,0.31313993174061433,0.013552671543623503,0 | |
| arc_easy,acc,0.6317340067340067,0.009897286209010892,0 | |
| arc_easy,acc_norm,0.6127946127946128,0.009995312065890341,0 | |
| boolq,acc,0.5758409785932722,0.008643869023388125,1 | |
| cb,acc,0.48214285714285715,0.0673769750864465,1 | |
| cb,f1,0.32495309568480296,,1 | |
| copa,acc,0.79,0.040936018074033256,0 | |
| hellaswag,acc,0.46106353316072496,0.004974628903829131,0 | |
| hellaswag,acc_norm,0.6156144194383589,0.004854555294017531,0 | |
| piqa,acc,0.7388465723612623,0.010248738649935576,0 | |
| piqa,acc_norm,0.7431991294885746,0.010192864802278039,0 | |
| rte,acc,0.51985559566787,0.030072723167317184,0 | |
| sciq,acc,0.89,0.009899393819724428,0 | |
| sciq,acc_norm,0.872,0.010570133761108665,0 | |
| storycloze_2016,acc,0.7167290219134153,0.010419760409155363,0 | |
| winogrande,acc,0.5864246250986582,0.0138409717631953,0 | |