lm1-misc-pile / 1b58b88b8 /1b58b88b8pile /evaluation /rankeval /lm1-1b5-8b8-results_lm-eval_global_step16765_2023-01-24-13-53-33_2shots.json
Muennighoff's picture
Add
46fa37e
raw
history blame contribute delete
No virus
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.307,
"acc_stderr": 0.01459328489285262
},
"anli_r2": {
"acc": 0.336,
"acc_stderr": 0.014944140233795027
},
"anli_r3": {
"acc": 0.3308333333333333,
"acc_stderr": 0.013588208070709
},
"cb": {
"acc": 0.44642857142857145,
"acc_stderr": 0.06703189227942398,
"f1": 0.2809560132214594
},
"copa": {
"acc": 0.66,
"acc_stderr": 0.04760952285695237
},
"hellaswag": {
"acc": 0.28540131447918743,
"acc_stderr": 0.0045068240943332985,
"acc_norm": 0.30790679147580163,
"acc_norm_stderr": 0.004606843344517482
},
"rte": {
"acc": 0.516245487364621,
"acc_stderr": 0.030080573208738064
},
"winogrande": {
"acc": 0.5043409629044988,
"acc_stderr": 0.014051956064076892
},
"storycloze_2016": {
"acc": 0.5660074826296099,
"acc_stderr": 0.011461234645182191
},
"boolq": {
"acc": 0.5617737003058104,
"acc_stderr": 0.008678056241208772
},
"arc_easy": {
"acc": 0.45454545454545453,
"acc_stderr": 0.010217299762709428,
"acc_norm": 0.4305555555555556,
"acc_norm_stderr": 0.010160345396860075
},
"arc_challenge": {
"acc": 0.20136518771331058,
"acc_stderr": 0.011718927477444272,
"acc_norm": 0.2440273037542662,
"acc_norm_stderr": 0.012551447627856253
},
"sciq": {
"acc": 0.798,
"acc_stderr": 0.012702651587655139,
"acc_norm": 0.766,
"acc_norm_stderr": 0.013394902889660009
},
"piqa": {
"acc": 0.6077257889009793,
"acc_stderr": 0.011391846744072232,
"acc_norm": 0.6169749727965179,
"acc_norm_stderr": 0.011342081709082845
}
},
"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
}
}