all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -0.6522728800773621,
    "eval_logits/rejected": -0.5080697536468506,
    "eval_logps/chosen": -476.88665771484375,
    "eval_logps/rejected": -369.71734619140625,
    "eval_loss": 0.6931471824645996,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 6.0198,
    "eval_samples": 5,
    "eval_samples_per_second": 0.831,
    "eval_steps_per_second": 0.166,
    "train_loss": 0.3465735912322998,
    "train_runtime": 21.9289,
    "train_samples": 3,
    "train_samples_per_second": 0.137,
    "train_steps_per_second": 0.046
}