all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.977890968322754,
    "eval_logits/rejected": -3.0260937213897705,
    "eval_logps/chosen": -519.8008422851562,
    "eval_logps/rejected": -565.180908203125,
    "eval_loss": 0.013797644525766373,
    "eval_rewards/accuracies": 0.9950494766235352,
    "eval_rewards/chosen": -2.1351423263549805,
    "eval_rewards/margins": 11.757019996643066,
    "eval_rewards/rejected": -13.892162322998047,
    "eval_runtime": 1401.9892,
    "eval_samples": 5359,
    "eval_samples_per_second": 4.61,
    "eval_steps_per_second": 0.144,
    "train_loss": 0.05705668801843857,
    "train_runtime": 30574.286,
    "train_samples": 48228,
    "train_samples_per_second": 1.902,
    "train_steps_per_second": 0.015
}