{
    "epoch": 0.9872958257713249,
    "eval_logits/chosen": 0.9563044309616089,
    "eval_logits/rejected": 0.865182638168335,
    "eval_logps/chosen": -121.97750854492188,
    "eval_logps/rejected": -149.4178924560547,
    "eval_loss": 0.6674867272377014,
    "eval_rewards/accuracies": 0.5666666626930237,
    "eval_rewards/chosen": -0.04618287831544876,
    "eval_rewards/margins": 0.046417996287345886,
    "eval_rewards/rejected": -0.09260086715221405,
    "eval_runtime": 4.5645,
    "eval_samples": 464,
    "eval_samples_per_second": 101.654,
    "eval_steps_per_second": 3.286,
    "total_flos": 0.0,
    "train_loss": 0.6753217893488267,
    "train_runtime": 321.7901,
    "train_samples": 8806,
    "train_samples_per_second": 27.366,
    "train_steps_per_second": 0.211
}