Muennighoff's picture
add
cc04ae0
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.346,
"acc_stderr": 0.015050266127564438
},
"anli_r2": {
"acc": 0.364,
"acc_stderr": 0.015222868840522024
},
"anli_r3": {
"acc": 0.3325,
"acc_stderr": 0.013605417345710526
},
"cb": {
"acc": 0.44642857142857145,
"acc_stderr": 0.067031892279424,
"f1": 0.31977105885280577
},
"copa": {
"acc": 0.8,
"acc_stderr": 0.04020151261036844
},
"hellaswag": {
"acc": 0.44851623182632944,
"acc_stderr": 0.004963259311700562,
"acc_norm": 0.5903206532563234,
"acc_norm_stderr": 0.004907694727935689
},
"rte": {
"acc": 0.5523465703971119,
"acc_stderr": 0.02993107036293953
},
"winogrande": {
"acc": 0.5643251775848461,
"acc_stderr": 0.01393570973961571
},
"storycloze_2016": {
"acc": 0.706574024585783,
"acc_stderr": 0.010529489334744471
},
"boolq": {
"acc": 0.5981651376146789,
"acc_stderr": 0.008574857171671134
},
"arc_easy": {
"acc": 0.5989057239057239,
"acc_stderr": 0.010057051106534372,
"acc_norm": 0.5812289562289562,
"acc_norm_stderr": 0.010123487160167819
},
"arc_challenge": {
"acc": 0.2832764505119454,
"acc_stderr": 0.013167478735134575,
"acc_norm": 0.3037542662116041,
"acc_norm_stderr": 0.01343890918477876
},
"sciq": {
"acc": 0.899,
"acc_stderr": 0.009533618929341002,
"acc_norm": 0.872,
"acc_norm_stderr": 0.010570133761108658
},
"piqa": {
"acc": 0.7426550598476604,
"acc_stderr": 0.01019992106479251,
"acc_norm": 0.7535364526659413,
"acc_norm_stderr": 0.010054810789671811
}
},
"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
}
}