Posts for: #fine-tuning

Predicting Disk Failures with a Small LLM, Part 2: Fixing the Evaluation

2026-10-16

#llm #fine-tuning #qlora #backblaze #hardware-failure #homelab

Correcting the baseline evaluation from Part 1 before training again: both the original and fine-tuned Qwen2.5-1.5B models predict no failure for every drive.

Predicting Disk Failures with a Small LLM, Part 1: A Working Pipeline and a Useless Model

2026-10-15

#llm #fine-tuning #qlora #backblaze #smart #hardware-failure #homelab

Fine-tuning Qwen2.5-1.5B with QLoRA on an RTX 3060 to predict hard drive failures from public Backblaze SMART data. Training worked; prediction did not.