| task,metric,value,err,version | |
| anli_r1,acc,0.317,0.014721675438880215,0 | |
| anli_r2,acc,0.36,0.015186527932040133,0 | |
| anli_r3,acc,0.3433333333333333,0.01371263383046586,0 | |
| arc_challenge,acc,0.2977815699658703,0.013363080107244484,0 | |
| arc_challenge,acc_norm,0.31569965870307165,0.01358257109581529,0 | |
| arc_easy,acc,0.6405723905723906,0.009845958893373766,0 | |
| arc_easy,acc_norm,0.6237373737373737,0.009940646221513774,0 | |
| boolq,acc,0.5889908256880734,0.008605429733982185,1 | |
| cb,acc,0.375,0.06527912098338669,1 | |
| cb,f1,0.26666666666666666,,1 | |
| copa,acc,0.79,0.04093601807403326,0 | |
| hellaswag,acc,0.4473212507468632,0.004962010338226347,0 | |
| hellaswag,acc_norm,0.5924118701453893,0.004903815885983272,0 | |
| piqa,acc,0.7154515778019587,0.010527218464130612,0 | |
| piqa,acc_norm,0.7268770402611534,0.010395730264453258,0 | |
| rte,acc,0.5631768953068592,0.029855247390314945,0 | |
| sciq,acc,0.877,0.010391293421849877,0 | |
| sciq,acc_norm,0.852,0.01123486636423525,0 | |
| storycloze_2016,acc,0.6926777124532336,0.010669445081866666,0 | |
| winogrande,acc,0.579321231254933,0.013874526372008315,0 | |