lm1-2b8-55b-c4-repetitions / evaluation /2b855b18bc4-results_lm-eval_global_step52452_2022-12-25-19-28-17.json
Muennighoff's picture
Add
6134937
raw
history blame
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.332,
"acc_stderr": 0.014899597242811485
},
"anli_r2": {
"acc": 0.332,
"acc_stderr": 0.01489959724281148
},
"anli_r3": {
"acc": 0.3441666666666667,
"acc_stderr": 0.013720551062295755
},
"cb": {
"acc": 0.44642857142857145,
"acc_stderr": 0.06703189227942398,
"f1": 0.32078853046594985
},
"copa": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446
},
"hellaswag": {
"acc": 0.43636725751842265,
"acc_stderr": 0.004949207947265915,
"acc_norm": 0.5636327424815774,
"acc_norm_stderr": 0.004949207947265913
},
"rte": {
"acc": 0.5451263537906137,
"acc_stderr": 0.029973636495415255
},
"winogrande": {
"acc": 0.5509076558800315,
"acc_stderr": 0.01397945938914085
},
"storycloze_2016": {
"acc": 0.6878674505611972,
"acc_stderr": 0.01071522034627968
},
"boolq": {
"acc": 0.590519877675841,
"acc_stderr": 0.008600549751320916
},
"arc_easy": {
"acc": 0.5723905723905723,
"acc_stderr": 0.010151683397430677,
"acc_norm": 0.5067340067340067,
"acc_norm_stderr": 0.010258852980991825
},
"arc_challenge": {
"acc": 0.25,
"acc_stderr": 0.012653835621466646,
"acc_norm": 0.2841296928327645,
"acc_norm_stderr": 0.013179442447653886
},
"sciq": {
"acc": 0.812,
"acc_stderr": 0.012361586015103754,
"acc_norm": 0.727,
"acc_norm_stderr": 0.014095022868717584
},
"piqa": {
"acc": 0.7448313384113167,
"acc_stderr": 0.010171571592521822,
"acc_norm": 0.7519042437431991,
"acc_norm_stderr": 0.010077118315574706
}
},
"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
}
}