Muennighoff's picture
add
f6c5fad
raw
history blame contribute delete
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.29,
"acc_stderr": 0.014356395999905689
},
"anli_r2": {
"acc": 0.365,
"acc_stderr": 0.015231776226264903
},
"anli_r3": {
"acc": 0.3333333333333333,
"acc_stderr": 0.013613950010225603
},
"cb": {
"acc": 0.6071428571428571,
"acc_stderr": 0.0658538889806635,
"f1": 0.4062342885872297
},
"copa": {
"acc": 0.73,
"acc_stderr": 0.044619604333847394
},
"hellaswag": {
"acc": 0.36168094005178253,
"acc_stderr": 0.004795051037917719,
"acc_norm": 0.45210117506472813,
"acc_norm_stderr": 0.004966832553245038
},
"rte": {
"acc": 0.5379061371841155,
"acc_stderr": 0.030009848912529117
},
"winogrande": {
"acc": 0.5122336227308603,
"acc_stderr": 0.01404827882040562
},
"storycloze_2016": {
"acc": 0.6344200962052379,
"acc_stderr": 0.011136758947688388
},
"boolq": {
"acc": 0.5663608562691131,
"acc_stderr": 0.008667690464344683
},
"arc_easy": {
"acc": 0.5370370370370371,
"acc_stderr": 0.010231597249131051,
"acc_norm": 0.5172558922558923,
"acc_norm_stderr": 0.010253671674754631
},
"arc_challenge": {
"acc": 0.21843003412969283,
"acc_stderr": 0.01207429160570098,
"acc_norm": 0.25597269624573377,
"acc_norm_stderr": 0.012753013241244518
},
"sciq": {
"acc": 0.889,
"acc_stderr": 0.009938701010583726,
"acc_norm": 0.875,
"acc_norm_stderr": 0.010463483381956722
},
"piqa": {
"acc": 0.704570184983678,
"acc_stderr": 0.010644731559342464,
"acc_norm": 0.705658324265506,
"acc_norm_stderr": 0.010633311470347519
}
},
"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
}
}