|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.327, |
|
"acc_stderr": 0.01484221315341124 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.332, |
|
"acc_stderr": 0.014899597242811492 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.34, |
|
"acc_stderr": 0.01368049572576779 |
|
}, |
|
"cb": { |
|
"acc": 0.5, |
|
"acc_stderr": 0.06741998624632421, |
|
"f1": 0.35057471264367807 |
|
}, |
|
"copa": { |
|
"acc": 0.8, |
|
"acc_stderr": 0.040201512610368445 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4731129257120096, |
|
"acc_stderr": 0.0049825618152141244, |
|
"acc_norm": 0.6270663214499104, |
|
"acc_norm_stderr": 0.004825963768772216 |
|
}, |
|
"rte": { |
|
"acc": 0.5306859205776173, |
|
"acc_stderr": 0.03003973059219781 |
|
}, |
|
"winogrande": { |
|
"acc": 0.574585635359116, |
|
"acc_stderr": 0.013895257666646378 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7140566541956174, |
|
"acc_stderr": 0.010449259851345842 |
|
}, |
|
"boolq": { |
|
"acc": 0.5788990825688073, |
|
"acc_stderr": 0.008635491562221344 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6031144781144782, |
|
"acc_stderr": 0.010039236800583209, |
|
"acc_norm": 0.5723905723905723, |
|
"acc_norm_stderr": 0.010151683397430673 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.28071672354948807, |
|
"acc_stderr": 0.013131238126975586, |
|
"acc_norm": 0.31313993174061433, |
|
"acc_norm_stderr": 0.013552671543623504 |
|
}, |
|
"sciq": { |
|
"acc": 0.892, |
|
"acc_stderr": 0.009820001651345696, |
|
"acc_norm": 0.89, |
|
"acc_norm_stderr": 0.009899393819724446 |
|
}, |
|
"piqa": { |
|
"acc": 0.7589771490750816, |
|
"acc_stderr": 0.009979042717267314, |
|
"acc_norm": 0.7616974972796517, |
|
"acc_norm_stderr": 0.009940334245876219 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |