Muennighoff's picture
Add eval
9e5d26a
raw
history blame
No virus
2.43 kB
{
"results": {
"anli_r1": {
"acc": 0.33,
"acc_stderr": 0.014876872027456734
},
"anli_r2": {
"acc": 0.344,
"acc_stderr": 0.015029633724408947
},
"anli_r3": {
"acc": 0.355,
"acc_stderr": 0.013819249004047301
},
"cb": {
"acc": 0.5,
"acc_stderr": 0.06741998624632421,
"f1": 0.42649620505163616
},
"copa": {
"acc": 0.77,
"acc_stderr": 0.04229525846816506
},
"hellaswag": {
"acc": 0.4567815176259709,
"acc_stderr": 0.0049711062650465545,
"acc_norm": 0.602867954590719,
"acc_norm_stderr": 0.004883037758919963
},
"rte": {
"acc": 0.5379061371841155,
"acc_stderr": 0.030009848912529117
},
"winogrande": {
"acc": 0.579321231254933,
"acc_stderr": 0.0138745263720083
},
"storycloze_2016": {
"acc": 0.7103153393907001,
"acc_stderr": 0.01048980809194661
},
"boolq": {
"acc": 0.608868501529052,
"acc_stderr": 0.008535239054221166
},
"arc_easy": {
"acc": 0.648989898989899,
"acc_stderr": 0.009793703885101047,
"acc_norm": 0.6452020202020202,
"acc_norm_stderr": 0.009817629113069696
},
"arc_challenge": {
"acc": 0.29948805460750855,
"acc_stderr": 0.013385021637313558,
"acc_norm": 0.3293515358361775,
"acc_norm_stderr": 0.013734057652635473
},
"sciq": {
"acc": 0.917,
"acc_stderr": 0.008728527206074789,
"acc_norm": 0.921,
"acc_norm_stderr": 0.00853415677333344
},
"piqa": {
"acc": 0.7410228509249184,
"acc_stderr": 0.010220966031405609,
"acc_norm": 0.7486398258977149,
"acc_norm_stderr": 0.01012115601681925
}
},
"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
}
}