eval_results.json

{
    "eval_HasAns_exact": 75.37112010796221,
    "eval_HasAns_f1": 81.67986330801969,
    "eval_HasAns_total": 5928,
    "eval_NoAns_exact": 82.70815811606391,
    "eval_NoAns_f1": 82.70815811606391,
    "eval_NoAns_total": 5945,
    "eval_best_exact": 79.04489177124569,
    "eval_best_exact_thresh": 0.0,
    "eval_best_f1": 82.1947468786271,
    "eval_best_f1_thresh": 0.0,
    "eval_exact": 79.04489177124569,
    "eval_f1": 82.19474687862723,
    "eval_model_preparation_time": 0.0008,
    "eval_runtime": 34.4454,
    "eval_samples": 12171,
    "eval_samples_per_second": 353.342,
    "eval_steps_per_second": 0.697,
    "eval_total": 11873
}