all_results.json

{
    "epoch": 1.0,
    "eval_logps/chosen": -2.7619028091430664,
    "eval_logps/rejected": -1.1848111152648926,
    "eval_loss": 19.815065383911133,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": -27.619028091430664,
    "eval_rewards/margins": -15.770916938781738,
    "eval_rewards/rejected": -11.848111152648926,
    "eval_runtime": 4.3531,
    "eval_samples": 12,
    "eval_samples_per_second": 2.757,
    "eval_steps_per_second": 0.689,
    "total_flos": 0.0,
    "train_loss": 21.83849455109725,
    "train_runtime": 4561.3354,
    "train_samples": 5640,
    "train_samples_per_second": 1.236,
    "train_steps_per_second": 0.124
}