Muennighoff's picture
Add
d7c2560
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.335,
"acc_stderr": 0.014933117490932575
},
"anli_r2": {
"acc": 0.333,
"acc_stderr": 0.014910846164229857
},
"anli_r3": {
"acc": 0.3416666666666667,
"acc_stderr": 0.013696658778002512
},
"cb": {
"acc": 0.4107142857142857,
"acc_stderr": 0.0663363415035954,
"f1": 0.1940928270042194
},
"copa": {
"acc": 0.83,
"acc_stderr": 0.03775251680686371
},
"hellaswag": {
"acc": 0.48207528380800635,
"acc_stderr": 0.004986573992451681,
"acc_norm": 0.6312487552280422,
"acc_norm_stderr": 0.004814803098436799
},
"rte": {
"acc": 0.5451263537906137,
"acc_stderr": 0.029973636495415252
},
"winogrande": {
"acc": 0.5832675611681136,
"acc_stderr": 0.013856250072796318
},
"storycloze_2016": {
"acc": 0.7252805986103688,
"acc_stderr": 0.010322309878339504
},
"boolq": {
"acc": 0.5804281345565749,
"acc_stderr": 0.008631175489166722
},
"arc_easy": {
"acc": 0.61489898989899,
"acc_stderr": 0.009985214798737247,
"acc_norm": 0.5349326599326599,
"acc_norm_stderr": 0.010234713052723684
},
"arc_challenge": {
"acc": 0.26791808873720135,
"acc_stderr": 0.012942030195136432,
"acc_norm": 0.2909556313993174,
"acc_norm_stderr": 0.013273077865907581
},
"sciq": {
"acc": 0.833,
"acc_stderr": 0.011800434324644586,
"acc_norm": 0.747,
"acc_norm_stderr": 0.01375427861358708
},
"piqa": {
"acc": 0.7616974972796517,
"acc_stderr": 0.009940334245876203,
"acc_norm": 0.7665941240478781,
"acc_norm_stderr": 0.009869247889520993
}
},
"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
}
}