all_results.json

{
    "epoch": 1.9973828840617638,
    "eval_logits/chosen": 4.600930213928223,
    "eval_logits/rejected": 4.9520039558410645,
    "eval_logps/chosen": -443.648193359375,
    "eval_logps/rejected": -378.15826416015625,
    "eval_loss": 0.6740825176239014,
    "eval_rewards/accuracies": 0.6150793433189392,
    "eval_rewards/chosen": -0.07192634046077728,
    "eval_rewards/margins": 0.26874542236328125,
    "eval_rewards/rejected": -0.34067174792289734,
    "eval_runtime": 20.4479,
    "eval_samples": 2000,
    "eval_samples_per_second": 97.81,
    "eval_steps_per_second": 3.081,
    "total_flos": 0.0,
    "train_loss": 0.675485389037702,
    "train_runtime": 5897.7907,
    "train_samples": 61134,
    "train_samples_per_second": 20.731,
    "train_steps_per_second": 0.162
}