paper-with-me

Papers

Checkpoint Merging via Bayesian Optimization in LLM Pretraining

2024-03-28 · Deyuan Liu, Zecheng Wang, Bingning Wang, WeiPeng Chen, Chunshan Li, Zhiying Tu, Dianhui Chu, Bo Li, Dianbo Sui

The rapid proliferation of large language models (LLMs) such as GPT-4 and Gemini underscores the intense demand for resources during their training processes, posing significant challenges due to substantial computational and environmental costs. To alleviate this issue, we propose checkpoint merging in pretraining LLM. This method utilizes LLM checkpoints with shared training trajectories, and is rooted in an extensive search space exploration for the best merging weight via Bayesian optimization. Through various experiments, we demonstrate that: (1) Our proposed methodology exhibits the capacity to augment pretraining, presenting an opportunity akin to obtaining substantial benefits at minimal cost; (2) Our proposed methodology, despite requiring a given held-out dataset, still demonstrates robust generalization capabilities across diverse domains, a pivotal aspect in pretraining.

📄 PDF Abstract BibTeX arXiv:2403.19390

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Optimization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

In-Context Learning for Latent Space Bayesian Optimization

2026-06-08 · Tuan A. Vu, Harri Lähdesmäki, Julien Martinelli arxiv

Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins. In parallel, tabular foundation mod…

If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs

2024-12-05 · Muhammad Khalifa, Yi-Chern Tan, Arash Ahmadian, Tom Hosking 외

Model merging has shown great promise at combining expert models, but the benefit of merging is unclear when merging ``generalist'' models trained on many tasks. We explore merging in the context of large (~100B) models,…

Code GenerationInstruction Following

On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm

2024-02-06 · Zhanpeng Zhou, Zijun Chen, Yilan Chen, Bo Zhang 외

The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning. In this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint an…

Leveraging free energy in pretraining model selection for improved fine-tuning

2024-10-08 · Michael Munn, Susan Wei

Recent advances in artificial intelligence have been fueled by the development of foundation models such as BERT, GPT, T5, and Vision Transformers. These models are first pretrained on vast and diverse datasets and then …

Model Selection

Harnessing Optimization Dynamics for Curvature-Informed Model Merging

2025-09-14 · Pouria Mahdavinia, Hamed Mahdavi, Niloofar Mireshghallah, Mehrdad Mahdavi arxiv

Model merging is an effective post-training strategy for composing capabilities in large language models without joint retraining. We study this in the supervised fine-tuning (SFT) stage, where multiple capability-based …

Instruction Following