Muennighoff's picture
add
cc04ae0
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.309,
"acc_stderr": 0.01461960097720649
},
"anli_r2": {
"acc": 0.336,
"acc_stderr": 0.014944140233795018
},
"anli_r3": {
"acc": 0.34833333333333333,
"acc_stderr": 0.013759437498874075
},
"cb": {
"acc": 0.44642857142857145,
"acc_stderr": 0.06703189227942398,
"f1": 0.3456203829338158
},
"copa": {
"acc": 0.77,
"acc_stderr": 0.04229525846816506
},
"hellaswag": {
"acc": 0.46036646086436966,
"acc_stderr": 0.004974080638364265,
"acc_norm": 0.6097390957976498,
"acc_norm_stderr": 0.004868117598481941
},
"rte": {
"acc": 0.5126353790613718,
"acc_stderr": 0.030086851767188564
},
"winogrande": {
"acc": 0.5627466456195738,
"acc_stderr": 0.013941393310695924
},
"storycloze_2016": {
"acc": 0.692143238909674,
"acc_stderr": 0.010674598158758186
},
"boolq": {
"acc": 0.617737003058104,
"acc_stderr": 0.008499149690449273
},
"arc_easy": {
"acc": 0.5753367003367004,
"acc_stderr": 0.010142653687480416,
"acc_norm": 0.5513468013468014,
"acc_norm_stderr": 0.010205540414612871
},
"arc_challenge": {
"acc": 0.2815699658703072,
"acc_stderr": 0.013143376735009022,
"acc_norm": 0.3054607508532423,
"acc_norm_stderr": 0.013460080478002498
},
"sciq": {
"acc": 0.848,
"acc_stderr": 0.01135891830347528,
"acc_norm": 0.845,
"acc_norm_stderr": 0.011450157470799475
},
"piqa": {
"acc": 0.7377584330794341,
"acc_stderr": 0.01026250256517245,
"acc_norm": 0.7404787812840044,
"acc_norm_stderr": 0.010227939888173923
}
},
"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
}
}