all_results.json

{
    "eval_HasAns_exact": 43.68252698920432,
    "eval_HasAns_f1": 51.86559486275948,
    "eval_HasAns_total": 5002,
    "eval_NoAns_exact": 50.40016006402561,
    "eval_NoAns_f1": 50.40016006402561,
    "eval_NoAns_total": 4998,
    "eval_best_exact": 50.02,
    "eval_best_exact_thresh": 0.0,
    "eval_best_f1": 51.163646740828945,
    "eval_best_f1_thresh": 0.0,
    "eval_exact": 47.04,
    "eval_f1": 51.13317055035233,
    "eval_runtime": 840.5387,
    "eval_samples": 10000,
    "eval_samples_per_second": 11.897,
    "eval_steps_per_second": 1.487,
    "eval_total": 10000
}