all_results.json

{
    "epoch": 3.0,
    "eval_average_metrics": 62.27396685546466,
    "eval_em": 52.6431718061674,
    "eval_f1": 71.90476190476191,
    "eval_loss": 0.22205480933189392,
    "eval_runtime": 24.5121,
    "eval_samples_per_second": 98.89,
    "test_average_metrics": 63.46612466124662,
    "test_em": 54.44444444444444,
    "test_f1": 72.48780487804879,
    "test_loss": 0.19974233210086823,
    "test_runtime": 25.265,
    "test_samples_per_second": 95.943,
    "train_loss": 0.18877839930180654,
    "train_runtime": 1478.3404,
    "train_samples": 27243,
    "train_samples_per_second": 55.284,
    "train_steps_per_second": 1.729
}