{ "epoch": 1.0, "eval_logits/chosen": -2.2779674530029297, "eval_logits/rejected": -2.0900180339813232, "eval_logps/chosen": -240.2975311279297, "eval_logps/rejected": -236.9312744140625, "eval_loss": 0.023918792605400085, "eval_rewards/accuracies": 0.6600000262260437, "eval_rewards/chosen": -0.04146282374858856, "eval_rewards/margins": 0.0851340964436531, "eval_rewards/rejected": -0.12659691274166107, "eval_runtime": 711.555, "eval_samples": 2000, "eval_samples_per_second": 2.811, "eval_steps_per_second": 1.405, "train_loss": 0.028345070170466266, "train_runtime": 172193.3354, "train_samples": 61135, "train_samples_per_second": 0.355, "train_steps_per_second": 0.089 }