{
    "epoch": 0.999244142101285,
    "eval_epsilon_dpo/beta": 0.005521266255527735,
    "eval_epsilon_dpo/beta_margin_grad_mean": -0.4411477744579315,
    "eval_epsilon_dpo/beta_margin_grad_std": 0.0961698442697525,
    "eval_epsilon_dpo/beta_margin_mean": 0.2462044507265091,
    "eval_epsilon_dpo/beta_margin_std": 0.40493056178092957,
    "eval_epsilon_dpo/loss_margin_mean": 45.06350326538086,
    "eval_kl/n_epsilon_steps": 0.28169015049934387,
    "eval_kl/p_epsilon_steps": 0.7174295783042908,
    "eval_logits/chosen": 0.043499208986759186,
    "eval_logits/rejected": -0.059857551008462906,
    "eval_logps/chosen": -169.52423095703125,
    "eval_logps/ref_chosen": -74.85946655273438,
    "eval_logps/ref_rejected": -79.54898834228516,
    "eval_logps/rejected": -219.27725219726562,
    "eval_loss": 0.5982230305671692,
    "eval_rewards/accuracies": 0.7174295783042908,
    "eval_rewards/chosen": -0.5240421295166016,
    "eval_rewards/margins": 0.2462044507265091,
    "eval_rewards/rejected": -0.770246684551239,
    "eval_runtime": 42.1471,
    "eval_samples": 2303,
    "eval_samples_per_second": 54.642,
    "eval_steps_per_second": 1.708
}