lm1-2b8-55b-c4-repetitions / evaluation_small /2b855b9bc4-results_lm-eval_global_step52452_2022-12-23-23-13-03.json
Muennighoff's picture
Add
6134937
raw
history blame
1.73 kB
{
"results": {
"copa": {
"acc": 0.72,
"acc_stderr": 0.04512608598542127
},
"boolq": {
"acc": 0.5963302752293578,
"acc_stderr": 0.008581220435616816
},
"hellaswag": {
"acc": 0.4334793865763792,
"acc_stderr": 0.004945424771611596,
"acc_norm": 0.560744871539534,
"acc_norm_stderr": 0.0049528205388318985
},
"arc_challenge": {
"acc": 0.25,
"acc_stderr": 0.012653835621466646,
"acc_norm": 0.28071672354948807,
"acc_norm_stderr": 0.013131238126975578
},
"arc_easy": {
"acc": 0.5458754208754208,
"acc_stderr": 0.010216507710244106,
"acc_norm": 0.49074074074074076,
"acc_norm_stderr": 0.010258024147860673
},
"sciq": {
"acc": 0.814,
"acc_stderr": 0.012310790208412803,
"acc_norm": 0.711,
"acc_norm_stderr": 0.014341711358296177
},
"winogrande": {
"acc": 0.5461720599842147,
"acc_stderr": 0.013992441563707068
},
"piqa": {
"acc": 0.7399347116430903,
"acc_stderr": 0.0102348932490613,
"acc_norm": 0.7426550598476604,
"acc_norm_stderr": 0.01019992106479251
},
"rte": {
"acc": 0.5487364620938628,
"acc_stderr": 0.029953149241808943
}
},
"versions": {
"copa": 0,
"boolq": 1,
"hellaswag": 0,
"arc_challenge": 0,
"arc_easy": 0,
"sciq": 0,
"winogrande": 0,
"piqa": 0,
"rte": 0
}
}