{ "epoch": 4.0, "eval_logits/chosen": -2.1607675552368164, "eval_logits/rejected": -2.156055450439453, "eval_logps/chosen": -33.63822555541992, "eval_logps/rejected": -37.278076171875, "eval_loss": 0.4762561619281769, "eval_rewards/accuracies": 0.5685215592384338, "eval_rewards/chosen": 0.27742961049079895, "eval_rewards/margins": 0.11044850200414658, "eval_rewards/rejected": 0.16698110103607178, "eval_runtime": 145.2249, "eval_samples": 343, "eval_samples_per_second": 2.362, "eval_steps_per_second": 0.296, "train_loss": 0.17319794591371115, "train_runtime": 10768.0107, "train_samples": 3079, "train_samples_per_second": 1.144, "train_steps_per_second": 0.143 }