{ "epoch": 0.9988571428571429, "eval_logits/chosen": 0.20247821509838104, "eval_logits/rejected": 1.7624026536941528, "eval_logps/chosen": -361.47540283203125, "eval_logps/rejected": -403.6280212402344, "eval_loss": 0.5172589421272278, "eval_rewards/accuracies": 0.7715517282485962, "eval_rewards/chosen": -0.8587150573730469, "eval_rewards/margins": 0.9868037104606628, "eval_rewards/rejected": -1.8455188274383545, "eval_runtime": 92.8884, "eval_samples": 1831, "eval_samples_per_second": 19.712, "eval_steps_per_second": 0.312, "total_flos": 0.0, "train_loss": 0.5608050315822016, "train_runtime": 10950.5403, "train_samples": 55999, "train_samples_per_second": 5.114, "train_steps_per_second": 0.04 }