paper-with-me

Papers

Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training

2024-10-31 · Atli Kosson, Bettina Messmer, Martin Jaggi

Learning Rate Warmup is a popular heuristic for training neural networks, especially at larger batch sizes, despite limited understanding of its benefits. Warmup decreases the update size $\Delta \mathbf{w}_t = \eta_t \mathbf{u}_t$ early in training by using lower values for the learning rate $\eta_t$. In this work we argue that warmup benefits training by keeping the overall size of $\Delta \mathbf{w}_t$ limited, counteracting large initial values of $\mathbf{u}_t$. Focusing on small-scale GPT training with AdamW/Lion, we explore the following question: Why and by which criteria are early updates $\mathbf{u}_t$ too large? We analyze different metrics for the update size including the $\ell_2$-norm, resulting directional change, and impact on the representations of the network, providing a new perspective on warmup. In particular, we find that warmup helps counteract large angular updates as well as a limited critical batch size early in training. Finally, we show that the need for warmup can be significantly reduced or eliminated by modifying the optimizer to explicitly normalize $\mathbf{u}_t$ based on the aforementioned metrics.

📄 PDF Abstract BibTeX arXiv:2410.23922

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

On the adequacy of untuned warmup for adaptive optimization

2019-10-09 · Jerry Ma, Denis Yarats

Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for the learning rate. Motivated by the difficulty of choosing and…

Image ClassificationLanguage ModellingMachine Translation

Why Warmup the Learning Rate? Underlying Mechanisms and Improvements

2024-06-13 · Dayal Singh Kalra, Maissam Barkeshli

It is common in deep learning to warm up the learning rate $\eta$, often by a linear schedule between $\eta_{\text{init}} = 0$ and a predetermined target $\eta_{\text{trgt}}$. In this paper, we show through systematic ex…

Large Batch Training Does Not Need Warmup

2020-02-04 · Zhouyuan Huo, Bin Gu, Heng Huang

Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. However, the optimizer converges slowly at early epochs and there is a gap between large-batch…

Let the Target Select for Itself: Data Selection via Target-Aligned Paths

2026-05-10 · Huitao Yang, Hengzhi He, Guang Cheng arxiv

Targeted data selection aims to identify training samples from a large candidate pool that improve performance on a specific downstream task. Many recent methods estimate candidate utility by aggregating local attributio…

Fast Certified Robust Training with Short Warmup

2021-03-31 · NeurIPS 2021 12 · Zhouxing Shi, Yihan Wang, huan zhang, JinFeng Yi 외

Recently, bound propagation based certified robust training methods have been proposed for training neural networks with certifiable robustness guarantees. Despite that state-of-the-art (SOTA) methods including interval …

Adversarial Defense