lm1-misc-pile / 221m60b60b /evaluation /rankeval /lm1-221m-60b-results_lm-eval_global_step115203_2023-01-22-18-55-49_0shots.json
Muennighoff's picture
Add
c305798
{
"results": {
"anli_r1": {
"acc": 0.338,
"acc_stderr": 0.01496596071022448
},
"anli_r2": {
"acc": 0.349,
"acc_stderr": 0.015080663991563102
},
"anli_r3": {
"acc": 0.3616666666666667,
"acc_stderr": 0.013876131663123872
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644647,
"f1": 0.3738576238576239
},
"copa": {
"acc": 0.66,
"acc_stderr": 0.04760952285695237
},
"hellaswag": {
"acc": 0.28978291177056364,
"acc_stderr": 0.004527343651130804,
"acc_norm": 0.3158733320055766,
"acc_norm_stderr": 0.004639126951051422
},
"rte": {
"acc": 0.5379061371841155,
"acc_stderr": 0.03000984891252912
},
"winogrande": {
"acc": 0.5074980268350434,
"acc_stderr": 0.014050905521228573
},
"storycloze_2016": {
"acc": 0.5964724746125066,
"acc_stderr": 0.011345169332729754
},
"boolq": {
"acc": 0.5217125382262997,
"acc_stderr": 0.008736805647519953
},
"arc_easy": {
"acc": 0.4541245791245791,
"acc_stderr": 0.010216507710244096,
"acc_norm": 0.4095117845117845,
"acc_norm_stderr": 0.010090368160990055
},
"arc_challenge": {
"acc": 0.19197952218430034,
"acc_stderr": 0.0115095989065981,
"acc_norm": 0.23037542662116042,
"acc_norm_stderr": 0.01230492841874761
},
"sciq": {
"acc": 0.785,
"acc_stderr": 0.012997843819031825,
"acc_norm": 0.7,
"acc_norm_stderr": 0.014498627873361425
},
"piqa": {
"acc": 0.6311207834602829,
"acc_stderr": 0.011257546676908804,
"acc_norm": 0.6305767138193689,
"acc_norm_stderr": 0.01126098862857233
}
},
"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
}
}