all_results.json

{
    "epoch": 1.971563981042654,
    "eval_logits/chosen": 96.502197265625,
    "eval_logits/rejected": 89.92664337158203,
    "eval_logps/chosen": -430.8598937988281,
    "eval_logps/rejected": -460.5821533203125,
    "eval_loss": 0.5234470367431641,
    "eval_rewards/accuracies": 0.6875,
    "eval_rewards/chosen": -3.3595829010009766,
    "eval_rewards/margins": 1.5659757852554321,
    "eval_rewards/rejected": -4.925559043884277,
    "eval_runtime": 124.8927,
    "eval_samples": 750,
    "eval_samples_per_second": 6.005,
    "eval_steps_per_second": 0.192,
    "total_flos": 0.0,
    "train_loss": 0.5405629426240921,
    "train_runtime": 2172.3856,
    "train_samples": 6750,
    "train_samples_per_second": 6.214,
    "train_steps_per_second": 0.048
}