{ "epoch": 1.971563981042654, "eval_logits/chosen": -26.960426330566406, "eval_logits/rejected": -25.98261260986328, "eval_logps/chosen": -386.185302734375, "eval_logps/rejected": -378.6257629394531, "eval_loss": 0.6492888331413269, "eval_rewards/accuracies": 0.6875, "eval_rewards/chosen": -0.04152223840355873, "eval_rewards/margins": 0.09864477068185806, "eval_rewards/rejected": -0.1401670128107071, "eval_runtime": 6.8392, "eval_samples": 750, "eval_samples_per_second": 109.662, "eval_steps_per_second": 3.509, "total_flos": 0.0, "train_loss": 0.661209049133154, "train_runtime": 432.2704, "train_samples": 6750, "train_samples_per_second": 31.23, "train_steps_per_second": 0.241 }