{
    "epoch": 1.994962216624685,
    "eval_dpo_loss": 0.6829819679260254,
    "eval_logits": -1.368598461151123,
    "eval_logps": -99.36083984375,
    "eval_loss": 1.0826873779296875,
    "eval_objective": 1.090183973312378,
    "eval_ranking_idealized": 0.5925414562225342,
    "eval_ranking_idealized_expo": 0.5165745615959167,
    "eval_ranking_simple": 0.5220994353294373,
    "eval_regularize": 0.40720194578170776,
    "eval_runtime": 235.7199,
    "eval_samples": 5790,
    "eval_samples_per_second": 24.563,
    "eval_steps_per_second": 1.536,
    "total_flos": 0.0,
    "train_loss": 1.010300681672313,
    "train_runtime": 13850.696,
    "train_samples": 50802,
    "train_samples_per_second": 7.336,
    "train_steps_per_second": 0.038
}