{
    "epoch": 0.9999018549416037,
    "eval_logits/chosen": -1.4624338150024414,
    "eval_logits/rejected": -1.4133074283599854,
    "eval_logps/chosen": -460.1110534667969,
    "eval_logps/rejected": -483.5314025878906,
    "eval_loss": 0.5487077236175537,
    "eval_rewards/accuracies": 0.7380239367485046,
    "eval_rewards/chosen": -1.126965880393982,
    "eval_rewards/margins": 0.6619576215744019,
    "eval_rewards/rejected": -1.7889233827590942,
    "eval_runtime": 296.9255,
    "eval_samples": 2000,
    "eval_samples_per_second": 6.736,
    "eval_steps_per_second": 1.125,
    "total_flos": 0.0,
    "train_loss": 0.5787653771390342,
    "train_runtime": 28047.1443,
    "train_samples": 61134,
    "train_samples_per_second": 2.18,
    "train_steps_per_second": 0.091
}