all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -3.25435733795166,
    "eval_logits/rejected": -3.204742431640625,
    "eval_logps/chosen": -433.63043212890625,
    "eval_logps/rejected": -429.45819091796875,
    "eval_loss": 0.6412035226821899,
    "eval_rewards/accuracies": 0.64453125,
    "eval_rewards/chosen": -0.10438449680805206,
    "eval_rewards/margins": 0.14497718214988708,
    "eval_rewards/rejected": -0.24936166405677795,
    "eval_runtime": 8.2917,
    "eval_samples": 2000,
    "eval_samples_per_second": 241.204,
    "eval_steps_per_second": 3.859,
    "total_flos": 0.0,
    "train_loss": 0.6571792745689967,
    "train_runtime": 784.6622,
    "train_samples": 61135,
    "train_samples_per_second": 77.913,
    "train_steps_per_second": 0.609
}