{
    "epoch": 0.9989528795811519,
    "eval_kl/n_epsilon_steps": 0.31703630089759827,
    "eval_kl/p_epsilon_steps": 0.6743951439857483,
    "eval_logits/chosen": -0.8084373474121094,
    "eval_logits/rejected": -0.7665925025939941,
    "eval_logps/chosen": -588.654052734375,
    "eval_logps/ref_chosen": -287.9388427734375,
    "eval_logps/ref_rejected": -266.7934875488281,
    "eval_logps/rejected": -683.635009765625,
    "eval_loss": 0.621621310710907,
    "eval_rewards/accuracies": 0.6955645084381104,
    "eval_rewards/chosen": -0.5053801536560059,
    "eval_rewards/margins": 0.19223107397556305,
    "eval_rewards/rejected": -0.6976111531257629,
    "eval_runtime": 50.6489,
    "eval_samples": 2000,
    "eval_samples_per_second": 39.488,
    "eval_steps_per_second": 1.244,
    "total_flos": 0.0,
    "train_loss": 2.463846208664356,
    "train_runtime": 4358.2481,
    "train_samples": 61135,
    "train_samples_per_second": 14.027,
    "train_steps_per_second": 0.109
}