{ "epoch": 3.0, "eval_logits/chosen": -3.070441722869873, "eval_logits/rejected": -3.0647687911987305, "eval_logps/chosen": -62.94335174560547, "eval_logps/rejected": -68.72457122802734, "eval_loss": 0.6871925592422485, "eval_rewards/accuracies": 0.5943308472633362, "eval_rewards/chosen": -0.04231457784771919, "eval_rewards/margins": 0.013129997998476028, "eval_rewards/rejected": -0.05544458329677582, "eval_runtime": 383.6672, "eval_samples": 4304, "eval_samples_per_second": 11.218, "eval_steps_per_second": 1.402, "total_flos": 0.0, "train_loss": 0.000466351711199581, "train_runtime": 50.9431, "train_samples": 92858, "train_samples_per_second": 5468.341, "train_steps_per_second": 341.793 }