HerbDev model-development proof of concept

Graph Neural Network (GCN-style)

This case study shows the complete model-training workflow: establish a baseline, inspect evidence, make a controlled optimization, rerun the model, and preserve the resulting artifacts.

Baseline

validation_accuracy	0.4
test_accuracy	0.475
nodes	240
train_seconds	0.01641

Optimization decision

Increase hidden message-passing capacity and train more gradually after the baseline showed sensitivity to a small hidden representation.

Optimized run

validation_accuracy	1.0
test_accuracy	1.0
nodes	240
train_seconds	0.06463

Training evidence

Baseline and optimized training loss comparison

Execution environment

platform	Linux-6.18.35-x86_64-with-glibc2.41
machine	x86_64
python	3.13.5
torch	2.10.0+cpu
device	cpu
mps_available	False
cuda_available	False
seed	42

What this demonstrates for a client

Model development is not a single training command. The useful work is creating a reproducible dataset, choosing a defensible baseline, measuring behavior, changing one thing for a reason, retesting, and preserving enough evidence to explain what happened. The same process scales to client data, larger models, and production infrastructure.

Have a model or dataset that needs improvement?

The next step is to define the business outcome, available data, constraints, and success metric, then design the smallest experiment that can prove whether machine learning is worth pursuing.