***** Eval results *****
2024-06-16 22:33:27.148495epoch = 10.0
eval_HasAns_exact = 40.50366377495157
eval_HasAns_f1 = 44.072135007775564
eval_HasAns_total = 11873
eval_best_exact = 77.4025098964036
eval_best_exact_thresh = 28.15625
eval_best_f1 = 80.97098112922765
eval_best_f1_thresh = 28.15625
eval_exact = 40.50366377495157
eval_f1 = 44.072135007775564
eval_runtime = 85.0565
eval_samples_per_second = 140.718
eval_steps_per_second = 2.21
eval_total = 11873