luria
Search
Search
Dark mode
Light mode
Reader mode
Explorer
Home
❯
examples
❯
Knowledge base
❯
record
❯
practices.d
practices.d
Graph View
2 items under this folder.
Aug 22, 2026
SOTA-001: Use a learning rate between 1e-4 and 1e-3 for most tasks
optimization
Aug 22, 2026
SOTA-002: Prefer decoupled weight decay to L2 regularization added to the loss
optimization