all_results.json

{
    "epoch": 0.998691442030882,
    "eval_logits/chosen": -11.360100746154785,
    "eval_logits/rejected": -11.085914611816406,
    "eval_logps/chosen": -459.7269592285156,
    "eval_logps/rejected": -488.03009033203125,
    "eval_loss": 0.5439372658729553,
    "eval_rewards/accuracies": 0.671999990940094,
    "eval_rewards/chosen": -0.9089793562889099,
    "eval_rewards/margins": 0.5084334015846252,
    "eval_rewards/rejected": -1.4174127578735352,
    "eval_runtime": 223.5785,
    "eval_samples": 2000,
    "eval_samples_per_second": 8.945,
    "eval_steps_per_second": 1.118,
    "total_flos": 0.0,
    "train_loss": 0.5785154289169632,
    "train_runtime": 17436.3201,
    "train_samples": 61134,
    "train_samples_per_second": 3.506,
    "train_steps_per_second": 0.027
}