all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.75989031791687,
    "eval_logits/rejected": -2.753535509109497,
    "eval_logps/chosen": -307.4615173339844,
    "eval_logps/rejected": -320.4450378417969,
    "eval_loss": 0.6764041185379028,
    "eval_rewards/accuracies": 0.565666675567627,
    "eval_rewards/chosen": -0.988508403301239,
    "eval_rewards/margins": 0.07645130157470703,
    "eval_rewards/rejected": -1.0649596452713013,
    "eval_runtime": 1679.0616,
    "eval_samples": 2994,
    "eval_samples_per_second": 1.783,
    "eval_steps_per_second": 0.223,
    "train_loss": 0.6566078573155155,
    "train_runtime": 38377.8314,
    "train_samples": 19996,
    "train_samples_per_second": 0.521,
    "train_steps_per_second": 0.033
}