{
    "epoch": 1.0,
    "eval_logits/chosen": -0.44726553559303284,
    "eval_logits/rejected": 0.045745834708213806,
    "eval_logps/chosen": -395.98583984375,
    "eval_logps/rejected": -470.54931640625,
    "eval_loss": 0.5046471357345581,
    "eval_rewards/accuracies": 0.7245509028434753,
    "eval_rewards/chosen": -1.1825801134109497,
    "eval_rewards/margins": 0.8755642771720886,
    "eval_rewards/rejected": -2.0581440925598145,
    "eval_runtime": 494.7185,
    "eval_samples": 2000,
    "eval_samples_per_second": 4.043,
    "eval_steps_per_second": 0.338,
    "train_loss": 0.5401819272219315,
    "train_runtime": 34352.758,
    "train_samples": 61135,
    "train_samples_per_second": 1.78,
    "train_steps_per_second": 0.015
}