Muennighoff's picture
add
cc04ae0
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.316,
"acc_stderr": 0.014709193056057127
},
"anli_r2": {
"acc": 0.337,
"acc_stderr": 0.014955087918653609
},
"anli_r3": {
"acc": 0.355,
"acc_stderr": 0.0138192490040473
},
"cb": {
"acc": 0.44642857142857145,
"acc_stderr": 0.06703189227942398,
"f1": 0.25805555555555554
},
"copa": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256
},
"hellaswag": {
"acc": 0.4627564230233021,
"acc_stderr": 0.004975919665116542,
"acc_norm": 0.6117307309300936,
"acc_norm_stderr": 0.004863603638367434
},
"rte": {
"acc": 0.5270758122743683,
"acc_stderr": 0.0300523034631437
},
"winogrande": {
"acc": 0.5824782951854776,
"acc_stderr": 0.013859978264440251
},
"storycloze_2016": {
"acc": 0.711918760021379,
"acc_stderr": 0.010472537019822576
},
"boolq": {
"acc": 0.5831804281345566,
"acc_stderr": 0.008623192108843677
},
"arc_easy": {
"acc": 0.5896464646464646,
"acc_stderr": 0.010093531255765457,
"acc_norm": 0.571969696969697,
"acc_norm_stderr": 0.01015294331642626
},
"arc_challenge": {
"acc": 0.27559726962457337,
"acc_stderr": 0.013057169655761841,
"acc_norm": 0.30204778156996587,
"acc_norm_stderr": 0.013417519144716413
},
"sciq": {
"acc": 0.834,
"acc_stderr": 0.011772110370812184,
"acc_norm": 0.793,
"acc_norm_stderr": 0.012818553557843986
},
"piqa": {
"acc": 0.7480957562568009,
"acc_stderr": 0.010128421335088683,
"acc_norm": 0.7595212187159956,
"acc_norm_stderr": 0.009971345364651066
}
},
"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
}
}