{ "epoch": 2.96, "eval_logits/chosen": 100.24970245361328, "eval_logits/rejected": 94.2728271484375, "eval_logps/chosen": -485.094482421875, "eval_logps/rejected": -504.0652160644531, "eval_loss": 0.5433239936828613, "eval_rewards/accuracies": 0.71875, "eval_rewards/chosen": -3.1689956188201904, "eval_rewards/margins": 2.082571268081665, "eval_rewards/rejected": -5.2515668869018555, "eval_runtime": 49.158, "eval_samples": 750, "eval_samples_per_second": 15.257, "eval_steps_per_second": 0.488, "train_loss": 0.27917395799587935, "train_runtime": 1799.8719, "train_samples": 6750, "train_samples_per_second": 11.251, "train_steps_per_second": 0.087 }