Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

• URL: http://arxiv.org/abs/2406.06563v1
• Date: Mon, 3 Jun 2024 03:58:41 GMT
• Title: Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
• Authors: Tianwen Wei, Bo Zhu, Liang Zhao, Cheng Cheng, Biye Li, Weiwei Lü, Peng Cheng, Jianhao Zhang, Xiaoyu Zhang, Liang Zeng, Xiaokun Wang, Yutuan Ma, Rui Hu, Shuicheng Yan, Han Fang, Yahui Zhou,
• Abstract summary: We introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (LLM) with 146 billion parameters and 16 experts. It is based on the pre-existing dense checkpoints of our Skywork-13B model.
• Score: 57.582219834039506
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this technical report, we introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (LLM) with 146 billion parameters and 16 experts. It is initialized from the pre-existing dense checkpoints of our Skywork-13B model. We explore the comparative effectiveness of upcycling versus training from scratch initializations. Our findings suggest that the choice between these two approaches should consider both the performance of the existing dense checkpoints and the MoE training budget. We highlight two innovative techniques: gating logit normalization, which improves expert diversification, and adaptive auxiliary loss coefficients, allowing for layer-specific adjustment of auxiliary loss coefficients. Our experimental results validate the effectiveness of these methods. Leveraging these techniques and insights, we trained our upcycled Skywork-MoE on a condensed subset of our SkyPile corpus. The evaluation results demonstrate that our model delivers strong performance across a wide range of benchmarks.

Related papers

• Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts [75.85448576746373]
  We propose a method of grouping and pruning similar experts to improve the model's parameter efficiency. We validate the effectiveness of our method by pruning three state-of-the-art MoE architectures. The evaluation shows that our method outperforms other model pruning methods on a range of natural language tasks.
  arXiv  Detail & Related papers  (2024-07-12T17:25:02Z)
• Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training [73.90260246781435]
  We present Lory, the first approach that scales such architectures to autoregressive language model pre-training. We show significant performance gains over parameter-matched dense models on both perplexity and a variety of downstream tasks. Despite segment-level routing, Lory models achieve competitive performance compared to state-of-the-art MoE models with token-level routing.
  arXiv  Detail & Related papers  (2024-05-06T03:06:33Z)
• SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection [51.99159169107426]
  We present our novel systems developed for the SemEval-2024 hallucination detection task. Our investigation spans a range of strategies to compare model predictions with reference standards. We introduce three distinct methods that exhibit strong performance metrics.
  arXiv  Detail & Related papers  (2024-04-09T09:03:44Z)
• Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer [59.43462055143123]
  The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning. In this study, we shed light on the homogeneous representation problem, wherein experts in the MoE fail to specialize and lack diversity. We propose an alternating training strategy that encourages each expert to update in a direction to the subspace spanned by other experts.
  arXiv  Detail & Related papers  (2023-10-15T07:20:28Z)
• Weighted Ensemble Self-Supervised Learning [67.24482854208783]
  Ensembling has proven to be a powerful technique for boosting model performance. We develop a framework that permits data-dependent weighted cross-entropy losses. Our method outperforms both in multiple evaluation metrics on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-11-18T02:00:17Z)

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.