{ "epoch": 1.0, "eval_logits/chosen": -2.22882342338562, "eval_logits/rejected": -2.223994731903076, "eval_logps/chosen": -34.021240234375, "eval_logps/rejected": -37.54384994506836, "eval_loss": 6.194193363189697, "eval_rewards/accuracies": 0.5664451718330383, "eval_rewards/chosen": 0.0026620819699019194, "eval_rewards/margins": 0.008108925074338913, "eval_rewards/rejected": -0.0054468438029289246, "eval_runtime": 145.4532, "eval_samples": 343, "eval_samples_per_second": 2.358, "eval_steps_per_second": 0.296, "train_loss": 5.437272009911475, "train_runtime": 3253.1823, "train_samples": 3079, "train_samples_per_second": 0.946, "train_steps_per_second": 0.118 }