DeepAI AI Chat
Log In Sign Up

On Layer Normalization in the Transformer Architecture

by   Ruibin Xiong, et al.

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyper-parameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications.


page 1

page 2

page 3

page 4


Understanding the Difficulty of Training Transformers

Transformers have been proved effective for many deep learning tasks. Tr...

Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers

Transformers have achieved great success in machine learning application...

Application of Transformers for Nonlinear Channel Compensation in Optical Systems

In this paper, we introduce a new nonlinear channel equalization method ...

On Layer Normalizations and Residual Connections in Transformers

In the perspective of a layer normalization (LN) position, the architect...

RealFormer: Transformer Likes Residual Attention

Transformer is the backbone of modern NLP models. In this paper, we prop...

Traveling Words: A Geometric Interpretation of Transformers

Transformers have significantly advanced the field of natural language p...

Code Repositories



view repo