{ "epoch": 0.9996020692399522, "eval_logits/chosen": 1.890890121459961, "eval_logits/rejected": 2.483922243118286, "eval_logps/chosen": -398.02276611328125, "eval_logps/rejected": -485.81976318359375, "eval_loss": 0.5341063737869263, "eval_rewards/accuracies": 0.72947758436203, "eval_rewards/chosen": -2.511190176010132, "eval_rewards/margins": 0.816419780254364, "eval_rewards/rejected": -3.3276097774505615, "eval_runtime": 347.9369, "eval_samples": 8552, "eval_samples_per_second": 24.579, "eval_steps_per_second": 0.385, "total_flos": 0.0, "train_loss": 0.5626794682566527, "train_runtime": 30362.0274, "train_samples": 160800, "train_samples_per_second": 5.296, "train_steps_per_second": 0.041 }