Related papers: Packing Analysis: Packing Is More Appropriate for …

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning…

Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inadequate training efficiency. Firstly, the utilization of…

Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks. In practice, SFT on a full dataset is computationally expensive and sometimes suffers from overfitting or bias…

In large language model training, input documents are typically concatenated together and then split into sequences of equal length to avoid padding tokens. Despite its efficiency, the concatenation approach compromises data integrity -- it…

Recent progress in motion forecasting has been substantially driven by self-supervised pre-training. However, adapting pre-trained models for specific downstream tasks, especially motion prediction, through extensive fine-tuning is often…

Full fine-tuning is a popular approach to adapt Transformer-based pre-trained large language models to a specific downstream task. However, the substantial requirements for computational power and storage have discouraged its widespread…

Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream…

Morphology-aware policy learning is a means of enhancing policy sample efficiency by aggregating data from multiple agents. These types of policies have previously been shown to help generalize over dynamic, kinematic, and limb…

This paper presents a systematic overview of parameter-efficient fine-tuning methods, covering over 50 papers published between early 2019 and mid-2024. These methods aim to address the challenges of fine-tuning large language models by…

Packing and shuffling tokens is a common practice in training auto-regressive language models (LMs) to prevent overfitting and improve efficiency. Typically documents are concatenated to chunks of maximum sequence length (MSL) and then…

Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally sub-optimal: heterogeneous learning dynamics cause…

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Parameter-efficient fine-tuning (PEFT) techniques have emerged to address overfitting and high computational costs associated with fully fine-tuning in self-supervised learning. Mainstream PEFT methods add a few trainable parameters while…

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage…

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural…

Pretrained foundation models learn embeddings that can be used for a wide range of downstream tasks. These embeddings optimise general performance, and if insufficiently accurate at a specific task the model can be fine-tuned to improve…

Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative…

Finetuning can be used to tackle domain-specific tasks by transferring knowledge. Previous studies on finetuning focused on adapting only the weights of a task-specific classifier or re-optimizing all layers of the pre-trained model using…

Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks.…