skills.rest
sovr610
sovr610COMMUNITY
Explore all skills by this author →
WebsiteGitHub

Hyperparameter Search

Automate phase-wise hyperparameter optimization for BrainAI training pipelines.

Updated Feb 28, 2026
Search Tags:#hyperparameter#bayesian-optimization#brain-ai#tpe#asha#lr-finder#phase-wise
One-click install
npx skills add https://github.com/sovr610/refffiy --skill hyperparameter-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Hyperparameter Search
Source: https://github.com/sovr610/refffiy/tree/main/brain-ai-dev/skills/hyperparameter-search
Command: npx skills add https://github.com/sovr610/refffiy --skill hyperparameter-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

BrainAI hyperparameter tuning is complex due to multi-phase training, conditional parameters, and expensive evaluations; this skill provides an automated, reproducible workflow to discover effective configurations.

Core Features & Use Cases

  • Phase-by-phase HPO for SNN, Encoders, HTM, Workspace, Decision, Reasoning, and Meta phases.
  • LR finder integration to prune the search space by learning rate bounds.
  • Bayesian optimization (TPE) and ASHA-based pruning with warm-starts and presets tailored for phase-specific tuning.
  • Experiment logging, parameter importance estimation, and CSV export for analysis.

Quick Start

Run LR range test to bound learning rate and then launch a Bayesian optimization run with ASHA pruning for phase-wise BrainAI configurations.

Frequently Asked Questions about Hyperparameter Search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I optimize hyperparameters across multiple training phases in BrainAI?▼

Phase-wise hyperparameter optimization automates tuning for BrainAI training phases by applying conditional parameter search and expensive evaluation handling to discover effective configurations.

What's the best way to bound the learning rate search space before running Bayesian optimization?▼

Use an LR finder integration to prune the search space by learning rate bounds before launching a Bayesian optimization run with ASHA pruning for phase-wise configurations.

How does ASHA pruning work with warm-start strategies for expensive training evaluations?▼

ASHA pruning terminates underperforming trials early while warm-start strategies bootstrap the search using phase-specific presets, reducing compute waste during expensive BrainAI training evaluations.

Do I need PyTorch to run the BrainAI hyperparameter tuning pipeline?▼

Yes, PyTorch is a required dependency, as the underlying BrainAI training pipeline relies on the torch framework to execute its phase-wise training and evaluation cycles.

Can I export trial logs and parameter importance estimations for reproducibility?▼

Yes, the workflow includes experiment logging, parameter importance estimation, and CSV export features to ensure trial data is logged and configurations remain reproducible.

Related Skills

Explore More Software Engineering Skills→
ChimeraFoundationaChimeraFoundationa

pytorch-lightning

Abstract PyTorch training boilerplate into LightningModule and Trainer workflows.

Community
Advanced
gyy0592gyy0592
7

gen-report-detailed

Generate detailed 13-section markdown experiment reports from flame_moonshot training logs and metrics.

Community
Advanced
NVIDIA-TAONVIDIA-TAO
83

tao-run-automl

Automate hyperparameter optimization for NVIDIA TAO networks with AutoMLRunner.

Official
Advanced
stanislavjiricekstanislavjiricek
6

phase-brain-optimize

Guide parameter exploration and model fitting for computational neuroscience.

Community
Intermediate