Muennighoff's picture
Add eval
d522938
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.348,
"acc_stderr": 0.015070604603768408
},
"anli_r2": {
"acc": 0.325,
"acc_stderr": 0.014818724459095527
},
"anli_r3": {
"acc": 0.3458333333333333,
"acc_stderr": 0.013736245342311012
},
"cb": {
"acc": 0.42857142857142855,
"acc_stderr": 0.06672848092813057,
"f1": 0.3018867924528302
},
"copa": {
"acc": 0.77,
"acc_stderr": 0.04229525846816505
},
"hellaswag": {
"acc": 0.4307906791475802,
"acc_stderr": 0.004941748817682304,
"acc_norm": 0.5699063931487751,
"acc_norm_stderr": 0.0049407715594755024
},
"rte": {
"acc": 0.5523465703971119,
"acc_stderr": 0.029931070362939526
},
"winogrande": {
"acc": 0.5469613259668509,
"acc_stderr": 0.0139903666321481
},
"storycloze_2016": {
"acc": 0.6969535008017104,
"acc_stderr": 0.01062761307337672
},
"boolq": {
"acc": 0.6110091743119266,
"acc_stderr": 0.008526800159503202
},
"arc_easy": {
"acc": 0.5942760942760943,
"acc_stderr": 0.010075755540128876,
"acc_norm": 0.5736531986531986,
"acc_norm_stderr": 0.010147858603835144
},
"arc_challenge": {
"acc": 0.26023890784982934,
"acc_stderr": 0.012821930225112563,
"acc_norm": 0.295221843003413,
"acc_norm_stderr": 0.013329750293382316
},
"sciq": {
"acc": 0.89,
"acc_stderr": 0.009899393819724439,
"acc_norm": 0.876,
"acc_norm_stderr": 0.01042749887234396
},
"piqa": {
"acc": 0.7383025027203483,
"acc_stderr": 0.01025563077270823,
"acc_norm": 0.7377584330794341,
"acc_norm_stderr": 0.010262502565172442
}
},
"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
}
}