{ "epoch": 1.0, "eval_logits/chosen": -2.5183939933776855, "eval_logits/rejected": -2.542128086090088, "eval_logps/chosen": -262.3270263671875, "eval_logps/rejected": -272.76593017578125, "eval_loss": 0.5167638063430786, "eval_rewards/accuracies": 0.76953125, "eval_rewards/chosen": 0.11419209837913513, "eval_rewards/margins": 1.047075629234314, "eval_rewards/rejected": -0.932883620262146, "eval_runtime": 110.44, "eval_samples": 2000, "eval_samples_per_second": 18.109, "eval_steps_per_second": 0.29, "train_loss": 0.5342033233602675, "train_runtime": 8549.6251, "train_samples": 61135, "train_samples_per_second": 7.151, "train_steps_per_second": 0.056 }