|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.328, |
|
"acc_stderr": 0.01485384248727033 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.364, |
|
"acc_stderr": 0.015222868840522022 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3516666666666667, |
|
"acc_stderr": 0.013789711695404785 |
|
}, |
|
"cb": { |
|
"acc": 0.48214285714285715, |
|
"acc_stderr": 0.0673769750864465, |
|
"f1": 0.4085858585858586 |
|
}, |
|
"copa": { |
|
"acc": 0.79, |
|
"acc_stderr": 0.040936018074033256 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.43069109739095796, |
|
"acc_stderr": 0.004941609820763584, |
|
"acc_norm": 0.5651264688309102, |
|
"acc_norm_stderr": 0.004947272454226218 |
|
}, |
|
"rte": { |
|
"acc": 0.5595667870036101, |
|
"acc_stderr": 0.029882123363118712 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5706393054459353, |
|
"acc_stderr": 0.013911537499969158 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6932121859967931, |
|
"acc_stderr": 0.010664275190473634 |
|
}, |
|
"boolq": { |
|
"acc": 0.6070336391437309, |
|
"acc_stderr": 0.008542335147970571 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5829124579124579, |
|
"acc_stderr": 0.010117738967781995, |
|
"acc_norm": 0.5782828282828283, |
|
"acc_norm_stderr": 0.010133255284012316 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.257679180887372, |
|
"acc_stderr": 0.012780770562768402, |
|
"acc_norm": 0.2738907849829352, |
|
"acc_norm_stderr": 0.013032004972989501 |
|
}, |
|
"sciq": { |
|
"acc": 0.893, |
|
"acc_stderr": 0.009779910359847167, |
|
"acc_norm": 0.884, |
|
"acc_norm_stderr": 0.010131468138756998 |
|
}, |
|
"piqa": { |
|
"acc": 0.7372143634385201, |
|
"acc_stderr": 0.010269354068140767, |
|
"acc_norm": 0.7415669205658324, |
|
"acc_norm_stderr": 0.01021397163677331 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |