{ "epoch": 1.0, "eval_logits/chosen": -2.689567804336548, "eval_logits/rejected": -2.664588451385498, "eval_logps/chosen": -230.68809509277344, "eval_logps/rejected": -235.1542205810547, "eval_loss": 0.27835845947265625, "eval_rewards/accuracies": 0.57421875, "eval_rewards/chosen": 31.905372619628906, "eval_rewards/margins": 4.392405033111572, "eval_rewards/rejected": 27.51296615600586, "eval_runtime": 96.4814, "eval_samples": 2000, "eval_samples_per_second": 20.729, "eval_steps_per_second": 0.332, "train_loss": 0.31381568898715734, "train_runtime": 7749.4814, "train_samples": 61134, "train_samples_per_second": 7.889, "train_steps_per_second": 0.062 }