all_results.json

{
    "epoch": 3.97,
    "eval_logits/chosen": -0.05778733268380165,
    "eval_logits/rejected": 0.0396571010351181,
    "eval_logps/chosen": -307.2596130371094,
    "eval_logps/rejected": -279.42071533203125,
    "eval_loss": 0.0018671295838430524,
    "eval_rewards/accuracies": 0.4869999885559082,
    "eval_rewards/chosen": -0.006934665143489838,
    "eval_rewards/margins": -0.0012784178834408522,
    "eval_rewards/rejected": -0.0056562479585409164,
    "eval_runtime": 412.8752,
    "eval_samples": 2000,
    "eval_samples_per_second": 4.844,
    "eval_steps_per_second": 1.211,
    "train_loss": 0.00108777264728316,
    "train_runtime": 2657.7329,
    "train_samples": 61135,
    "train_samples_per_second": 1.505,
    "train_steps_per_second": 0.093
}