Scaling Law for Post-training after Model Pruning

• URL: http://arxiv.org/abs/2411.10272v1
• Date: Fri, 15 Nov 2024 15:28:42 GMT
• Title: Scaling Law for Post-training after Model Pruning
• Authors: Xiaodong Chen, Yuxuan Hu, Jing Zhang, Xiaokang Zhang, Cuiping Li, Hong Chen,
• Abstract summary: Large language models (LLMs) based on the Transformer architecture are widely employed across various domains and tasks. To mitigate this, model pruning techniques have been developed to create more efficient models while maintaining high performance. This paper investigates the post-training requirements of pruned LLMs and introduces a scaling law to determine the optimal amount of post-training data.
• Score: 24.9935656519956
• License:
• Abstract: Large language models (LLMs) based on the Transformer architecture are widely employed across various domains and tasks. However, their increasing size imposes significant hardware demands, limiting practical deployment. To mitigate this, model pruning techniques have been developed to create more efficient models while maintaining high performance. Despite this, post-training after pruning is crucial for performance recovery and can be resource-intensive. This paper investigates the post-training requirements of pruned LLMs and introduces a scaling law to determine the optimal amount of post-training data. Post-training experiments with the Llama-3 and Qwen-2.5 series models, pruned using depth pruning, width pruning, and 2:4 semi-structured pruning, show that higher pruning ratios necessitate more post-training data for performance recovery, whereas larger LLMs require less. The proposed scaling law predicts a model's loss based on its parameter counts before and after pruning, as well as the post-training token counts. Furthermore, we find that the scaling law established from smaller LLMs can be reliably extrapolated to larger LLMs. This work provides valuable insights into the post-training of pruned LLMs and offers a practical scaling law for optimizing post-training data usage.

Related papers

• Pruning Foundation Models for High Accuracy without Retraining [48.256389781305415]
  It is challenging to deploy foundation models or large language models (LLMs) due to their massive parameters and computations. Post-training pruning methods are proposed to prune LLMs in one-shot without retraining. Our experiments demonstrate the superior performance of the proposed methods in comparison to SOTA baselines.
  arXiv  Detail & Related papers  (2024-10-21T01:23:34Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods [5.135352292810664]
  We show that simple depth pruning can effectively compress large language models (LLMs) Our pruning method boosts inference speeds, especially under memory-constrained conditions. We hope this work can help build compact yet capable LLMs.
  arXiv  Detail & Related papers  (2024-02-05T09:44:49Z)
• Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs [67.38165028487242]
  We introduce Dynamic Sparse No Training (DSnoT), a training-free fine-tuning approach to fine-tune large language models (LLMs) Inspired by the Dynamic Sparse Training, DSnoT minimizes the reconstruction error between the dense and sparse LLMs. Our paper offers fresh insights into how to fine-tune sparse LLMs in an efficient training-free manner and open new venues to scale the great potential of sparsity to LLMs.
  arXiv  Detail & Related papers  (2023-10-13T07:38:52Z)
• Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning [52.29522018586365]
  We study structured pruning as an effective means to develop smaller LLMs from pre-trained, larger models. Our approach employs two key techniques: (1) targeted structured pruning, which prunes a larger model to a specified target shape by removing layers, heads, and intermediate and hidden dimensions in an end-to-end manner, and (2) dynamic batch loading, which dynamically updates the composition of sampled data in each training batch based on varying losses across different domains.
  arXiv  Detail & Related papers  (2023-10-10T15:13:30Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.