rob-base-superqa2 / eval_results.json
nbroad's picture
nbroad HF staff
results
a97da1f
{
"epoch": 2.0,
"eval_HasAns_exact": 69.19611355371003,
"eval_HasAns_f1": 75.75383941256567,
"eval_HasAns_total": 18423,
"eval_NoAns_exact": 77.6109552879063,
"eval_NoAns_f1": 77.6109552879063,
"eval_NoAns_total": 6061,
"eval_best_exact": 71.27920274464957,
"eval_best_exact_thresh": 0.0,
"eval_best_f1": 76.21356737043324,
"eval_best_f1_thresh": 0.0,
"eval_exact": 71.27920274464957,
"eval_f1": 76.21356737043327,
"eval_samples": 44895,
"eval_total": 24484
}