From samples to adapters: SFT + LoRA →
Follow ten modules through data gates, supervised training, low-rank adaptation and independent evaluation.
Post-training practice
A planned project covering data, training, evaluation, and integration for a task within the AI testing workflow. Write-up in progress.
Problem
A planned project covering data, training, evaluation, and integration for a task within the AI testing workflow. Write-up in progress.
My work
Plan to define the task, data and evaluation, run training experiments, and integrate the model. Practice details are being updated.
Engineering choice
Implementation and boundaries are detailed in the articles below.
Engineering visualizations
Project articles
All articles →Search or filter language
START HERE
Post-training for a testing workflow
Plan error attribution, grouped samples, untrained baselines, and adoption criteria for missing side-effect assertions. Training has not started.