IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining

• URL: http://arxiv.org/abs/2503.05920v1
• Date: Fri, 07 Mar 2025 20:35:31 GMT
• Title: IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining
• Authors: Yixiao Li, Xianzhi Du, Ajay Jaiswal, Tao Lei, Tuo Zhao, Chong Wang, Jianyu Wang,
• Abstract summary: We propose an integrated enlarge-and-prune pipeline, which combines enlarge model training, pruning, and recovery.<n>We conduct experiments on compressing 2.8B models to 1.3B with up to 2T tokens in pretraining.<n>It demonstrates the integrated approach not only provides insights into the token efficiency of enlarged model pretraining but also achieves superior performance of pruned models.
• Score: 50.53912352342753
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training target-size models from scratch. In this paper, we advocate incorporating enlarged model pretraining, which is often ignored in previous works, into pruning. We study the enlarge-and-prune pipeline as an integrated system to address two critical questions: whether it is worth pretraining an enlarged model even when the model is never deployed, and how to optimize the entire pipeline for better pruned models. We propose an integrated enlarge-and-prune pipeline, which combines enlarge model training, pruning, and recovery under a single cosine annealing learning rate schedule. This approach is further complemented by a novel iterative structured pruning method for gradual parameter removal. The proposed method helps to mitigate the knowledge loss caused by the rising learning rate in naive enlarge-and-prune pipelines and enable effective redistribution of model capacity among surviving neurons, facilitating smooth compression and enhanced performance. We conduct comprehensive experiments on compressing 2.8B models to 1.3B with up to 2T tokens in pretraining. It demonstrates the integrated approach not only provides insights into the token efficiency of enlarged model pretraining but also achieves superior performance of pruned models.

Related papers

• MultiPruner: Balanced Structure Removal in Foundation Models [1.8434042562191815]
  Recently, state-of-the-art approaches for pruning large pre-trained models (LPMs) have demonstrated that the training-free removal of non-critical residual blocks in Transformers is viable for reducing model size.<n>We extend BlockPruner and propose MultiPruner, a pruning approach that surpasses recent training-free pruning methods by adopting a multidimensional, iterative, fine-grained pruning strategy.
  arXiv  Detail & Related papers  (2025-01-17T04:24:31Z)
• Optimizing Large Model Training through Overlapped Activation Recomputation [24.28543166026873]
  We present Lynx, a new recomputation framework to reduce overhead by overlapping recomputation with communication in training pipelines. Our comprehensive evaluation using GPT models with 1.3B-23B parameters shows that Lynx outperforms existing recomputation approaches by up to 1.37x.
  arXiv  Detail & Related papers  (2024-06-13T02:31:36Z)
• LaCo: Large Language Model Pruning via Layer Collapse [56.92068213969036]
  Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion. Existing methods such as model quantization, knowledge distillation, and model pruning are constrained by various issues. We propose a concise layer-wise structured pruner called textitLayer Collapse (LaCo), in which rear model layers collapse into a prior layer.
  arXiv  Detail & Related papers  (2024-02-17T04:16:30Z)
• An Emulator for Fine-Tuning Large Language Models using Small Language Models [91.02498576056057]
  We introduce emulated fine-tuning (EFT), a principled and practical method for sampling from a distribution that approximates the result of pre-training and fine-tuning at different scales. We show that EFT enables test-time adjustment of competing behavioral traits like helpfulness and harmlessness without additional training. Finally, a special case of emulated fine-tuning, which we call LM up-scaling, avoids resource-intensive fine-tuning of large pre-trained models by ensembling them with small fine-tuned models.
  arXiv  Detail & Related papers  (2023-10-19T17:57:16Z)
• PELA: Learning Parameter-Efficient Models with Low-Rank Approximation [16.9278983497498]
  We propose a novel method for increasing the parameter efficiency of pre-trained models by introducing an intermediate pre-training stage. This allows for direct and efficient utilization of the low-rank model for downstream fine-tuning tasks.
  arXiv  Detail & Related papers  (2023-10-16T07:17:33Z)
• Structural Pruning for Diffusion Models [65.02607075556742]
  We present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones. Our empirical assessment, undertaken across several datasets highlights two primary benefits of our proposed method.
  arXiv  Detail & Related papers  (2023-05-18T12:38:21Z)
• Dynamic Model Pruning with Feedback [64.019079257231]
  We propose a novel model compression method that generates a sparse trained model without additional overhead. We evaluate our method on CIFAR-10 and ImageNet, and show that the obtained sparse models can reach the state-of-the-art performance of dense models.
  arXiv  Detail & Related papers  (2020-06-12T15:07:08Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.