{ "epoch": 4.0, "eval_logits/chosen": -2.829094648361206, "eval_logits/rejected": -2.8266069889068604, "eval_logps/chosen": -33.231201171875, "eval_logps/rejected": -37.228851318359375, "eval_loss": 0.8066554665565491, "eval_rewards/accuracies": 0.5917773842811584, "eval_rewards/chosen": -1.1692489385604858, "eval_rewards/margins": 0.3491671681404114, "eval_rewards/rejected": -1.518416166305542, "eval_runtime": 112.7022, "eval_samples": 343, "eval_samples_per_second": 3.043, "eval_steps_per_second": 0.382, "train_loss": 0.21652605050763526, "train_runtime": 11213.836, "train_samples": 3079, "train_samples_per_second": 1.098, "train_steps_per_second": 0.137 }