all_results.json

{
    "epoch": 2.0,
    "eval_logits/chosen": 0.7331738471984863,
    "eval_logits/rejected": 0.7520135045051575,
    "eval_logps/chosen": -93.26776885986328,
    "eval_logps/rejected": -96.37944030761719,
    "eval_loss": 0.00928194634616375,
    "eval_rewards/accuracies": 0.3499999940395355,
    "eval_rewards/chosen": -0.015403981320559978,
    "eval_rewards/margins": 0.006420300807803869,
    "eval_rewards/rejected": -0.02182428352534771,
    "eval_runtime": 272.4398,
    "eval_samples": 2000,
    "eval_samples_per_second": 7.341,
    "eval_steps_per_second": 0.459,
    "train_loss": 0.008370190804172112,
    "train_runtime": 12459.0229,
    "train_samples": 30567,
    "train_samples_per_second": 4.907,
    "train_steps_per_second": 0.077
}