all_results.json

{
    "epoch": 2.999297541394882,
    "eval_logits/chosen": -0.06038603559136391,
    "eval_logits/rejected": 0.01924268528819084,
    "eval_logps/chosen": -1.7989143133163452,
    "eval_logps/rejected": -2.58301043510437,
    "eval_loss": 0.6509566903114319,
    "eval_rewards/accuracies": 0.6735904812812805,
    "eval_rewards/chosen": -1.7989143133163452,
    "eval_rewards/margins": 0.7840961217880249,
    "eval_rewards/rejected": -2.58301043510437,
    "eval_runtime": 40.198,
    "eval_samples": 1345,
    "eval_samples_per_second": 33.459,
    "eval_steps_per_second": 8.383,
    "total_flos": 0.0,
    "train_loss": 0.6513626721822561,
    "train_runtime": 30253.6444,
    "train_samples": 59790,
    "train_samples_per_second": 5.929,
    "train_steps_per_second": 0.185
}