all_results.json

{
    "epoch": 4.0,
    "eval_logits/chosen": -2.1405961513519287,
    "eval_logits/rejected": -2.13584041595459,
    "eval_logps/chosen": -34.389774322509766,
    "eval_logps/rejected": -38.05939865112305,
    "eval_loss": 0.9278836846351624,
    "eval_rewards/accuracies": 0.5747508406639099,
    "eval_rewards/chosen": -0.14208722114562988,
    "eval_rewards/margins": 0.0750228762626648,
    "eval_rewards/rejected": -0.21711009740829468,
    "eval_runtime": 145.1138,
    "eval_samples": 343,
    "eval_samples_per_second": 2.364,
    "eval_steps_per_second": 0.296,
    "train_loss": 0.2625940967689861,
    "train_runtime": 10748.6274,
    "train_samples": 3079,
    "train_samples_per_second": 1.146,
    "train_steps_per_second": 0.143
}