all_results.json

{
    "epoch": 0.9982631930527722,
    "eval_logits/chosen": 0.011077426373958588,
    "eval_logits/rejected": 0.0017527370946481824,
    "eval_logps/chosen": -0.3363344073295593,
    "eval_logps/rejected": -0.4006253778934479,
    "eval_loss": 1.2414826154708862,
    "eval_rewards/accuracies": 0.5914633870124817,
    "eval_rewards/chosen": -0.3363344073295593,
    "eval_rewards/margins": 0.06429095566272736,
    "eval_rewards/rejected": -0.4006253778934479,
    "eval_runtime": 424.6606,
    "eval_samples": 1961,
    "eval_samples_per_second": 4.618,
    "eval_steps_per_second": 0.29,
    "total_flos": 0.0,
    "train_loss": 1.248079635857004,
    "train_runtime": 20917.8016,
    "train_samples": 59876,
    "train_samples_per_second": 2.862,
    "train_steps_per_second": 0.022
}