eval_results.json

{
    "epoch": 3.0,
    "eval_accuracy": 0.87925,
    "eval_classification_report": "              precision    recall  f1-score     support\n0              0.908042  0.935314  0.921476  3030.00000\n1              0.777019  0.704124  0.738778   970.00000\naccuracy       0.879250  0.879250  0.879250     0.87925\nmacro avg      0.842531  0.819719  0.830127  4000.00000\nweighted avg   0.876269  0.879250  0.877172  4000.00000",
    "eval_confusion_matrix": "[[2834  196]\n [ 287  683]]",
    "eval_confusion_matrix_norm": "[[0.93531353 0.06468647]\n [0.29587629 0.70412371]]",
    "eval_f1": 0.7387777176852353,
    "eval_f1_macro": 0.8301269502098749,
    "eval_f1_weighted": 0.8771718049600645,
    "eval_loss": 0.4823172092437744,
    "eval_runtime": 9.6229,
    "eval_samples": 4000,
    "eval_samples_per_second": 415.677,
    "eval_steps_per_second": 25.98
}