{ "epoch": 1.97, "eval_logits/chosen": 92.81997680664062, "eval_logits/rejected": 86.46841430664062, "eval_logps/chosen": -429.9114685058594, "eval_logps/rejected": -459.4852600097656, "eval_loss": 0.4695254862308502, "eval_rewards/accuracies": 0.71875, "eval_rewards/chosen": -3.3745555877685547, "eval_rewards/margins": 1.5969535112380981, "eval_rewards/rejected": -4.9715094566345215, "eval_runtime": 52.4051, "eval_samples": 750, "eval_samples_per_second": 14.312, "eval_steps_per_second": 0.458, "train_loss": 0.38887147261546207, "train_runtime": 1183.8142, "train_samples": 6750, "train_samples_per_second": 11.404, "train_steps_per_second": 0.088 }