all_results.json

{
    "epoch": 4.0,
    "eval_logits/chosen": -2.2275288105010986,
    "eval_logits/rejected": -2.2226884365081787,
    "eval_logps/chosen": -34.09955978393555,
    "eval_logps/rejected": -37.600067138671875,
    "eval_loss": 0.693101167678833,
    "eval_rewards/accuracies": 0.5070598125457764,
    "eval_rewards/chosen": -0.026001954451203346,
    "eval_rewards/margins": 0.007375751622021198,
    "eval_rewards/rejected": -0.03337770700454712,
    "eval_runtime": 145.5528,
    "eval_samples": 343,
    "eval_samples_per_second": 2.357,
    "eval_steps_per_second": 0.295,
    "train_loss": 0.2942203808140445,
    "train_runtime": 10768.7061,
    "train_samples": 3079,
    "train_samples_per_second": 1.144,
    "train_steps_per_second": 0.143
}