Muennighoff's picture
Merge eval
5443e66
raw
history blame
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.315,
"acc_stderr": 0.014696631960792498
},
"anli_r2": {
"acc": 0.341,
"acc_stderr": 0.014998131348402702
},
"anli_r3": {
"acc": 0.34,
"acc_stderr": 0.0136804957257678
},
"cb": {
"acc": 0.14285714285714285,
"acc_stderr": 0.04718416136255829,
"f1": 0.143010752688172
},
"copa": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256
},
"hellaswag": {
"acc": 0.4473212507468632,
"acc_stderr": 0.004962010338226347,
"acc_norm": 0.5848436566421031,
"acc_norm_stderr": 0.0049174193677660296
},
"rte": {
"acc": 0.4729241877256318,
"acc_stderr": 0.0300523034631437
},
"winogrande": {
"acc": 0.601420678768745,
"acc_stderr": 0.013760357176873838
},
"storycloze_2016": {
"acc": 0.7156600748262961,
"acc_stderr": 0.01043161412866526
},
"boolq": {
"acc": 0.6119266055045871,
"acc_stderr": 0.008523130584760851
},
"arc_easy": {
"acc": 0.5593434343434344,
"acc_stderr": 0.010187264635711983,
"acc_norm": 0.5298821548821548,
"acc_norm_stderr": 0.010241444322886432
},
"arc_challenge": {
"acc": 0.2636518771331058,
"acc_stderr": 0.01287592915129705,
"acc_norm": 0.2858361774744027,
"acc_norm_stderr": 0.013203196088537369
},
"sciq": {
"acc": 0.906,
"acc_stderr": 0.009233052000787738,
"acc_norm": 0.902,
"acc_norm_stderr": 0.009406619184621226
},
"piqa": {
"acc": 0.7089227421109902,
"acc_stderr": 0.010598612490942586,
"acc_norm": 0.7143634385201306,
"acc_norm_stderr": 0.010539303948661916
}
},
"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
}
}