|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.329, |
|
"acc_stderr": 0.014865395385928362 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.314, |
|
"acc_stderr": 0.014683991951087962 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.345, |
|
"acc_stderr": 0.01372842153945487 |
|
}, |
|
"cb": { |
|
"acc": 0.39285714285714285, |
|
"acc_stderr": 0.0658538889806635, |
|
"f1": 0.33259154725720075 |
|
}, |
|
"copa": { |
|
"acc": 0.71, |
|
"acc_stderr": 0.045604802157206845 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.45717984465245964, |
|
"acc_stderr": 0.004971449552787172, |
|
"acc_norm": 0.6106353316072496, |
|
"acc_norm_stderr": 0.00486609688094144 |
|
}, |
|
"rte": { |
|
"acc": 0.5090252707581228, |
|
"acc_stderr": 0.030091559826331334 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5974743488555643, |
|
"acc_stderr": 0.013782866831703044 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7226082308925709, |
|
"acc_stderr": 0.010353267472010768 |
|
}, |
|
"boolq": { |
|
"acc": 0.5767584097859327, |
|
"acc_stderr": 0.008641391399113598 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6325757575757576, |
|
"acc_stderr": 0.009892552616211555, |
|
"acc_norm": 0.6376262626262627, |
|
"acc_norm_stderr": 0.009863468202583773 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.31399317406143346, |
|
"acc_stderr": 0.013562691224726281, |
|
"acc_norm": 0.3216723549488055, |
|
"acc_norm_stderr": 0.013650488084494162 |
|
}, |
|
"sciq": { |
|
"acc": 0.926, |
|
"acc_stderr": 0.008282064512704159, |
|
"acc_norm": 0.941, |
|
"acc_norm_stderr": 0.007454835650406725 |
|
}, |
|
"piqa": { |
|
"acc": 0.7442872687704026, |
|
"acc_stderr": 0.010178690109459862, |
|
"acc_norm": 0.7562568008705114, |
|
"acc_norm_stderr": 0.010017199471500609 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |