Transformer Hyper-Connection Discovery
Evolve custom manifold hyper-connection modules inside a fixed transformer NanoGPT training stack with 4 hyper-connections on the Shakespeare dataset, evaluated with 3 benchmark random seeds.
Tasks Explorer
This page focuses on example task setups only: task type, seeds, and evolution parameters for each run configuration. Best-node artifacts are shown on the dedicated Best Node page.
Example Task Definitions
These tasks are examples, not hard-coded limits of CliffSearch. The evolutionary loop is task-agnostic: to use CliffSearch on a custom problem, you supply a benchmark that is interfaced with the search runtime and exposes the artifact contract plus the primary metric to optimize.
Optimizer Discovery
Evolve EvoOptimizer(torch.optim.Optimizer) while keeping a regular NanoGPT stack on the Shakespeare dataset fixed, again evaluated with 3 benchmark random seeds.
Native Optimizer Discovery
Example ablation task: evolve EvoOptimizer(torch.optim.Optimizer) on small native classification benchmarks with linear and MLP models; the reported validation loss is averaged over 32 benchmark runs per node across 4 datasets, 2 seeds, and a 2x2 learning-rate/weight-decay grid.
Filters
Configurations
| Task | Bundle | Prompt | Mode | Seeds | Status |
|---|