{ "epoch": 2.986175115207373, "eval_logits/chosen": -1.9310764074325562, "eval_logits/rejected": -1.954269289970398, "eval_logps/chosen": -298.78546142578125, "eval_logps/rejected": -260.6278381347656, "eval_loss": 0.544903576374054, "eval_rewards/accuracies": 0.8299999833106995, "eval_rewards/chosen": 2.958364963531494, "eval_rewards/margins": 3.1445722579956055, "eval_rewards/rejected": -0.18620729446411133, "eval_runtime": 104.2849, "eval_samples_per_second": 14.738, "eval_steps_per_second": 0.24, "total_flos": 1909982962384896.0, "train_loss": 0.24334129419775657, "train_runtime": 6038.8466, "train_samples_per_second": 6.87, "train_steps_per_second": 0.027 }