|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.306, |
|
"acc_stderr": 0.014580006055436969 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.33, |
|
"acc_stderr": 0.014876872027456734 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3308333333333333, |
|
"acc_stderr": 0.013588208070709007 |
|
}, |
|
"cb": { |
|
"acc": 0.25, |
|
"acc_stderr": 0.058387420812114225, |
|
"f1": 0.2376010151606224 |
|
}, |
|
"copa": { |
|
"acc": 0.79, |
|
"acc_stderr": 0.040936018074033256 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.47679745070703045, |
|
"acc_stderr": 0.004984405935541087, |
|
"acc_norm": 0.6308504282015535, |
|
"acc_norm_stderr": 0.004815882719278393 |
|
}, |
|
"rte": { |
|
"acc": 0.48736462093862815, |
|
"acc_stderr": 0.030086851767188564 |
|
}, |
|
"winogrande": { |
|
"acc": 0.6101026045777427, |
|
"acc_stderr": 0.013707547317008462 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7199358631747729, |
|
"acc_stderr": 0.01038376499392048 |
|
}, |
|
"boolq": { |
|
"acc": 0.5889908256880734, |
|
"acc_stderr": 0.008605429733982185 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6388888888888888, |
|
"acc_stderr": 0.00985601342581124, |
|
"acc_norm": 0.6182659932659933, |
|
"acc_norm_stderr": 0.009968648851839672 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.29948805460750855, |
|
"acc_stderr": 0.013385021637313565, |
|
"acc_norm": 0.3148464163822526, |
|
"acc_norm_stderr": 0.01357265770308495 |
|
}, |
|
"sciq": { |
|
"acc": 0.902, |
|
"acc_stderr": 0.009406619184621238, |
|
"acc_norm": 0.89, |
|
"acc_norm_stderr": 0.009899393819724444 |
|
}, |
|
"piqa": { |
|
"acc": 0.750272034820457, |
|
"acc_stderr": 0.010099232969867488, |
|
"acc_norm": 0.763873775843308, |
|
"acc_norm_stderr": 0.009908965890558218 |
|
} |
|
}, |
|
"versions": { |
|
"anli_r1": 0, |
|
"anli_r2": 0, |
|
"anli_r3": 0, |
|
"cb": 1, |
|
"copa": 0, |
|
"hellaswag": 0, |
|
"rte": 0, |
|
"winogrande": 0, |
|
"storycloze_2016": 0, |
|
"boolq": 1, |
|
"arc_easy": 0, |
|
"arc_challenge": 0, |
|
"sciq": 0, |
|
"piqa": 0 |
|
} |
|
} |