Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models
GeMoE adaptively sets the number of experts per token via gating entropy, retaining 99.5% of static-routing performance while raising average sparsity by 36.5%.
-
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
SARA aligns internal routing distributions in MoE layers to high-resource semantic anchors via symmetric JS divergence, improving low-resource language performance by 0.8-1.2% over standard instruction tuning on Global-MMLU.
-
HDMoE: A Hierarchical Decoupling-Fusion Mixture-of-Experts Framework for Multimodal Cancer Survival Prediction
HDMoE uses hierarchical MoE and RFR modules to address redundant information and fine-grained intra/inter-modality relationships in multimodal cancer survival prediction, with positive results on private liver cancer ...
-
Hierarchical Mixture-of-Experts with Two-Stage Optimization
Hi-MoE uses two-level hierarchical routing objectives to enforce group-level balance while promoting within-group specialization, yielding better perplexity and expert utilization than prior MoE baselines in NLP and v...
-
Cubit: Token Mixer with Kernel Ridge Regression
Cubit replaces Transformer attention with Kernel Ridge Regression token mixing and shows potential gains on longer sequences.
-
MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter an...
-
Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource
MoE models with activation rates in an optimal region outperform dense LLMs of identical total parameter count, training compute, and data budget, with the optimal region consistent across scales.
-
Optimization Hyper-parameter Laws for Large Language Models
Opt-Laws predicts LLM final training loss from LR schedules via SDE-derived convergence and escape features, with 94% Top-2 hit rate on held-out schedules and F1=0.92 for divergence detection.
-
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
DAG-MoE uses a lightweight module to learn DAG-based structural aggregation of selected experts, expanding combination space and enabling intra-layer multi-step reasoning compared to standard weighted-sum MoE.
-
Cubit: Token Mixer with Kernel Ridge Regression
Cubit replaces Transformer's attention with a closed-form Kernel Ridge Regression token mixer and reports larger gains as training sequence length increases.
-
Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts
Orthogonal growth recycles pre-trained MoE checkpoints via layer copying and noisy expert duplication, delivering 10.6% higher accuracy than training from scratch with equivalent extra compute.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.