Thinking Machines ships Dimuon optimizer for LoRA fine-tuning, beats AdamW in fewer steps
simonguozirui · x · 2026-10-15
Thinking Machines introduced Dimuon, a new optimizer built for LoRA fine-tuning on its Tinker platform. In SFT tests it often reaches lower loss in fewer steps than AdamW; it's still experimental and available to try today. Tinker's docs also add optimizer guidance covering learning rates and mid-flight optimizer switching.
Related event: Thinking Machines Releases Dimuon Optimizer for LoRA Fine-Tuning(2 posts)→
More from Research
- DecisionRobust benchmark stress-tests 30 decision models against prompt injection and perturbations — Yifan Lan · 2026-10-15
- Continuum Attention: continuous integration beats softmax attention in all paired comparisons — Afshin Khadangi · 2026-10-15
- Researchers accuse an AI lab paper of overlapping their ARTS work without attribution — xwang_lk · 2026-10-15
- RootPath launches BinderVerse: AI-designed binders get wet-lab data in as few as 3 days — iskander · 2026-10-15
- New arXiv paper shows unconstrained MLIPs face exponentially ill-conditioned sampling limits — CatAstro_Piyush · 2026-10-15
- Paper: method-transferable ML potentials can outperform the quantum-chemical methods they trained on — CatAstro_Piyush · 2026-10-15