Muennighoff's picture
Add eval
26c6985
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.34,
"acc_stderr": 0.014987482264363937
},
"anli_r2": {
"acc": 0.327,
"acc_stderr": 0.014842213153411245
},
"anli_r3": {
"acc": 0.345,
"acc_stderr": 0.013728421539454876
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644648,
"f1": 0.3647798742138364
},
"copa": {
"acc": 0.83,
"acc_stderr": 0.037752516806863715
},
"hellaswag": {
"acc": 0.4731129257120096,
"acc_stderr": 0.004982561815214123,
"acc_norm": 0.6240788687512447,
"acc_norm_stderr": 0.004833699243292339
},
"rte": {
"acc": 0.5415162454873647,
"acc_stderr": 0.029992535385373314
},
"winogrande": {
"acc": 0.5982636148382005,
"acc_stderr": 0.013778439266649492
},
"storycloze_2016": {
"acc": 0.7226082308925709,
"acc_stderr": 0.010353267472010765
},
"boolq": {
"acc": 0.5302752293577981,
"acc_stderr": 0.008729009003964295
},
"arc_easy": {
"acc": 0.6687710437710438,
"acc_stderr": 0.009657641311350912,
"acc_norm": 0.6734006734006734,
"acc_norm_stderr": 0.009623047038267656
},
"arc_challenge": {
"acc": 0.3242320819112628,
"acc_stderr": 0.013678810399518815,
"acc_norm": 0.34215017064846415,
"acc_norm_stderr": 0.013864152159177278
},
"sciq": {
"acc": 0.925,
"acc_stderr": 0.008333333333333356,
"acc_norm": 0.932,
"acc_norm_stderr": 0.007964887911291605
},
"piqa": {
"acc": 0.7600652883569097,
"acc_stderr": 0.009963625892809544,
"acc_norm": 0.7709466811751904,
"acc_norm_stderr": 0.009804509865175504
}
},
"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
}
}