Muennighoff's picture
Add
f526fda
raw
history blame contribute delete
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.344,
"acc_stderr": 0.015029633724408943
},
"anli_r2": {
"acc": 0.374,
"acc_stderr": 0.015308767369006356
},
"anli_r3": {
"acc": 0.34833333333333333,
"acc_stderr": 0.01375943749887407
},
"cb": {
"acc": 0.42857142857142855,
"acc_stderr": 0.06672848092813058,
"f1": 0.19999999999999998
},
"copa": {
"acc": 0.77,
"acc_stderr": 0.04229525846816505
},
"hellaswag": {
"acc": 0.4715196176060546,
"acc_stderr": 0.004981680090303699,
"acc_norm": 0.6269667396932882,
"acc_norm_stderr": 0.004826224784850446
},
"rte": {
"acc": 0.48736462093862815,
"acc_stderr": 0.030086851767188564
},
"winogrande": {
"acc": 0.5864246250986582,
"acc_stderr": 0.013840971763195304
},
"storycloze_2016": {
"acc": 0.7327632282202031,
"acc_stderr": 0.010233145255103061
},
"boolq": {
"acc": 0.6168195718654435,
"acc_stderr": 0.008503021391450788
},
"arc_easy": {
"acc": 0.6262626262626263,
"acc_stderr": 0.009927267058259625,
"acc_norm": 0.61489898989899,
"acc_norm_stderr": 0.009985214798737251
},
"arc_challenge": {
"acc": 0.302901023890785,
"acc_stderr": 0.013428241573185349,
"acc_norm": 0.3242320819112628,
"acc_norm_stderr": 0.01367881039951882
},
"sciq": {
"acc": 0.912,
"acc_stderr": 0.008963053962592078,
"acc_norm": 0.896,
"acc_norm_stderr": 0.009658016218524301
},
"piqa": {
"acc": 0.7529923830250272,
"acc_stderr": 0.010062268140772624,
"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
}
}