Muennighoff's picture
add
cc04ae0
raw
history blame
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.339,
"acc_stderr": 0.014976758771620342
},
"anli_r2": {
"acc": 0.323,
"acc_stderr": 0.014794927843348644
},
"anli_r3": {
"acc": 0.3441666666666667,
"acc_stderr": 0.013720551062295756
},
"cb": {
"acc": 0.5,
"acc_stderr": 0.06741998624632421,
"f1": 0.3261261261261261
},
"copa": {
"acc": 0.81,
"acc_stderr": 0.03942772444036623
},
"hellaswag": {
"acc": 0.4643497311292571,
"acc_stderr": 0.004977081808179424,
"acc_norm": 0.6074487153953396,
"acc_norm_stderr": 0.004873203269366301
},
"rte": {
"acc": 0.5270758122743683,
"acc_stderr": 0.030052303463143706
},
"winogrande": {
"acc": 0.5777426992896606,
"acc_stderr": 0.013881582030658549
},
"storycloze_2016": {
"acc": 0.7129877071084981,
"acc_stderr": 0.010460934115933261
},
"boolq": {
"acc": 0.5773700305810398,
"acc_stderr": 0.008639722698719023
},
"arc_easy": {
"acc": 0.6056397306397306,
"acc_stderr": 0.010028176038393004,
"acc_norm": 0.5606060606060606,
"acc_norm_stderr": 0.010184134315437663
},
"arc_challenge": {
"acc": 0.2721843003412969,
"acc_stderr": 0.013006600406423706,
"acc_norm": 0.3037542662116041,
"acc_norm_stderr": 0.013438909184778764
},
"sciq": {
"acc": 0.847,
"acc_stderr": 0.01138950045966553,
"acc_norm": 0.792,
"acc_norm_stderr": 0.012841374572096928
},
"piqa": {
"acc": 0.7535364526659413,
"acc_stderr": 0.010054810789671824,
"acc_norm": 0.7595212187159956,
"acc_norm_stderr": 0.009971345364651068
}
},
"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
}
}