Posts by tag 'python'

Mar 29, 2026 · Ruby Jha · project-deep-dives

LoRA Hit 96% of Full Fine-Tuning. The Default Learning Rate Almost Killed It.

I fine-tuned all-MiniLM-L6-v2 on dating profiles, flipped Spearman from -0.22 to +0.85, and found LoRA hit 96.2% of that with 0.32% of parameters.

Mar 21, 2026 · Ruby Jha · project-deep-dives

I Tested 16 RAG Configs So You Don't Have To: Embedding Choice Matters More Than Chunk Size

Grid search across 16 RAG configurations reveals embedding model selection drives 26% more retrieval quality than chunk tuning.

Feb 28, 2026 · Ruby Jha · project-deep-dives

How I Calibrated an LLM Judge That Approved Everything

My first LLM judge had a 0% failure rate. That meant it was useless. This is the story of calibrating it to actually catch failures, and building a correction loop that took synthetic data failures from 36 to zero.