{ "epoch": 0.9999813887699838, "eval_logits/chosen": -2.6875, "eval_logits/rejected": -2.640625, "eval_logps/chosen": -568.0, "eval_logps/rejected": -660.0, "eval_loss": 0.4865521490573883, "eval_rewards/accuracies": 0.7406647801399231, "eval_rewards/chosen": -3.40625, "eval_rewards/margins": 1.21875, "eval_rewards/rejected": -4.625, "eval_runtime": 5083.2718, "eval_samples": 191184, "eval_samples_per_second": 37.586, "eval_steps_per_second": 0.587, "total_flos": 0.0, "train_loss": 0.0, "train_runtime": 18.6514, "train_samples": 3438778, "train_samples_per_second": 184371.069, "train_steps_per_second": 1440.375 }