all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -0.7062377333641052,
    "eval_logits/rejected": -0.9040690064430237,
    "eval_logps/chosen": -834.8738403320312,
    "eval_logps/rejected": -1456.362060546875,
    "eval_loss": 0.5792528390884399,
    "eval_rewards/accuracies": 0.77173912525177,
    "eval_rewards/chosen": -0.1323184221982956,
    "eval_rewards/margins": 0.34403395652770996,
    "eval_rewards/rejected": -0.47635239362716675,
    "eval_runtime": 330.6189,
    "eval_samples": 2927,
    "eval_samples_per_second": 8.853,
    "eval_steps_per_second": 0.278,
    "train_loss": 0.20238888480446554,
    "train_runtime": 919.6394,
    "train_samples": 10540,
    "train_samples_per_second": 11.461,
    "train_steps_per_second": 0.179
}