all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.744652509689331,
    "eval_logits/rejected": -2.71529483795166,
    "eval_logps/chosen": -297.10400390625,
    "eval_logps/rejected": -327.4286193847656,
    "eval_loss": 0.46045970916748047,
    "eval_rewards/accuracies": 0.78125,
    "eval_rewards/chosen": -0.5052940249443054,
    "eval_rewards/margins": 1.3699172735214233,
    "eval_rewards/rejected": -1.8752113580703735,
    "eval_runtime": 52.3218,
    "eval_samples": 1000,
    "eval_samples_per_second": 19.113,
    "eval_steps_per_second": 0.306,
    "train_loss": 0.48803097129668166,
    "train_runtime": 7971.1784,
    "train_samples": 61966,
    "train_samples_per_second": 7.774,
    "train_steps_per_second": 0.243
}