Muennighoff's picture
add files
f80bf0d
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.34,
"acc_stderr": 0.014987482264363937
},
"anli_r2": {
"acc": 0.309,
"acc_stderr": 0.014619600977206491
},
"anli_r3": {
"acc": 0.3233333333333333,
"acc_stderr": 0.01350837286730021
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644647,
"f1": 0.36467236467236464
},
"copa": {
"acc": 0.67,
"acc_stderr": 0.04725815626252607
},
"hellaswag": {
"acc": 0.36367257518422624,
"acc_stderr": 0.0048007281387923775,
"acc_norm": 0.4482174865564629,
"acc_norm_stderr": 0.004962949784236045
},
"rte": {
"acc": 0.516245487364621,
"acc_stderr": 0.030080573208738064
},
"winogrande": {
"acc": 0.5217048145224941,
"acc_stderr": 0.014039239216484636
},
"storycloze_2016": {
"acc": 0.632816675574559,
"acc_stderr": 0.011147041781368654
},
"boolq": {
"acc": 0.5146788990825688,
"acc_stderr": 0.008741285568667916
},
"arc_easy": {
"acc": 0.5336700336700336,
"acc_stderr": 0.010236494647406476,
"acc_norm": 0.5193602693602694,
"acc_norm_stderr": 0.010252089491165522
},
"arc_challenge": {
"acc": 0.2431740614334471,
"acc_stderr": 0.012536554144587087,
"acc_norm": 0.2645051194539249,
"acc_norm_stderr": 0.012889272949313368
},
"sciq": {
"acc": 0.895,
"acc_stderr": 0.009698921026024963,
"acc_norm": 0.893,
"acc_norm_stderr": 0.00977991035984717
},
"piqa": {
"acc": 0.690968443960827,
"acc_stderr": 0.01078141946440698,
"acc_norm": 0.6942328618063112,
"acc_norm_stderr": 0.010749627366141646
}
},
"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
}
}