过去几年，我们普遍沿用自回归的经验来设置 Encoder 的训练预算，而论文给出的闭式解表明，两者的最优配比不在同一个数量级。这意味着，在很多场景里，Encoder 的训练消耗明显超出了最佳区间。

Hold on - AI and Deep Learning are that easy? Of course, it’s not that easy: There is a big difference between using a model and training a model. Before we can reach the point where we have such a ...