Language Modeling on OOD
1.285LossMuon
Evaluation Results
| Method | Links | |
|---|---|---|
| MuonOptimizer=Muon, Model Size=3B2026.04 | 1.285 | |
| Adam+NexusOptimizer=Adam+Nexus, Model Size=3B2026.04 | 1.29 | |
| NexusModel Size=3B, Optimizer=Nexus2026.04 | 1.29 | |
| AdamWOptimizer=AdamW, Model Size=3B2026.04 | 1.302 | |
| AdamWModel Size=3B, Optimizer=AdamW2026.04 | 1.302 | |
| NexusModel Size=1B, Optimizer=Nexus2026.04 | 1.428 | |
| AdamWModel Size=1B, Optimizer=AdamW2026.04 | 1.433 |