all_results.json

{
    "epoch": 0.9880609304240429,
    "eval_logits/chosen": 9.236642837524414,
    "eval_logits/rejected": 10.05230712890625,
    "eval_logps/chosen": -0.37632718682289124,
    "eval_logps/rejected": -0.38437822461128235,
    "eval_loss": 1.3848165273666382,
    "eval_rewards/accuracies": 0.5268518328666687,
    "eval_rewards/chosen": -0.7526543736457825,
    "eval_rewards/margins": 0.01610211282968521,
    "eval_rewards/rejected": -0.7687564492225647,
    "eval_runtime": 164.7496,
    "eval_samples": 1080,
    "eval_samples_per_second": 6.555,
    "eval_steps_per_second": 1.639,
    "total_flos": 0.0,
    "train_loss": 1.3847383244832356,
    "train_runtime": 7739.7873,
    "train_samples": 9715,
    "train_samples_per_second": 1.255,
    "train_steps_per_second": 0.01
}