{"schema_version":"newruntime-agent-readable-v0.2","type":"post","stable_id":"post:fireworks-lora-fullft-three-test-protocol","slug":"fireworks-lora-fullft-three-test-protocol","title":"Run Three Tests Before Replacing LoRA With Full Fine-Tuning","description":"Fireworks shows how data coverage, optimization, and adapter capacity can create or close an apparent quality gap between LoRA and full fine-tuning.","retrieval_nugget":"Fireworks shows how data coverage, optimization, and adapter capacity can create or close an apparent quality gap between LoRA and full fine-tuning. When a simple LoRA run loses to full fine-tuning, the adapter may not be the limiting factor. Fireworks tested Qwen3.5-9B on three programmatically scored tasks and organized the diagnosis around data coverage, optimization, and adapter capacity.","status":"published","published_at":"2026-08-03","updated_at":"2026-08-03","record_date":"2026-08-03","date_kind":"published_at","topics":["post-training","open-models","evals","inference"],"source_urls":["https://fireworks.ai/blog/three-tests-to-run-before-you-switch-from-LoRa-to-FullFT"],"visuals":[{"id":"fireworks-lora-fullft-three-test-protocol","kind":"editorial-diagram","role":"hero","src":"https://newruntime.com/images/posts/fireworks-lora-fullft-three-test-protocol.webp","alt":"Hand-drawn diagnostic ladder that tests broader training coverage, a tuned optimization recipe, and increased adapter rank before comparing LoRA and full fine-tuning on quality and total deployment cost.","caption":"A FullFT advantage becomes meaningful only after coverage, recipe, and adapter-capacity alternatives have been tested under a declared comparison budget.","credit":"New Runtime synthesis from Fireworks AI","source_url":"https://fireworks.ai/blog/three-tests-to-run-before-you-switch-from-LoRa-to-FullFT","generated_with":"gemini-3.1-flash-image","width":1600,"height":900,"legend":[{"label":"Coverage","description":"Broaden task variation before interpreting an out-of-distribution failure as a method limit."},{"label":"Optimization","description":"Sweep learning rate and schedule because the best adapter recipe can differ sharply from FullFT."},{"label":"Capacity","description":"Increase rank under controlled scaling and check whether validity and exact quality move together."},{"label":"Economics","description":"Compare training and serving costs after both methods meet the required quality bar."}]}],"routes":{"html":"https://newruntime.com/posts/fireworks-lora-fullft-three-test-protocol/","markdown":"https://newruntime.com/posts/fireworks-lora-fullft-three-test-protocol.md","json":"https://newruntime.com/posts/fireworks-lora-fullft-three-test-protocol.json"},"source_format":"markdown","next_reads":[{"type":"topic","path":"/topics/evals/","reason":"Explore the evals topic hub.","url":"https://newruntime.com/topics/evals/","title":"Agent evals - New Runtime","media_type":"text/html"},{"type":"topic","path":"/topics/inference/","reason":"Explore the inference topic hub.","url":"https://newruntime.com/topics/inference/","title":"Inference - New Runtime","media_type":"text/html"},{"type":"related_material","path":"/posts/cerebras-moe-router-gradient-null-expert/","reason":"Shares evals and open models.","url":"https://newruntime.com/posts/cerebras-moe-router-gradient-null-expert/","title":"A Balanced MoE Router Can Still Be Functionally Dead","media_type":"text/html"},{"type":"related_material","path":"/posts/sequoia-open-model-dependency-paradox/","reason":"Shares open models and post training.","url":"https://newruntime.com/posts/sequoia-open-model-dependency-paradox/","title":"Open Weights Can Still Create A Strategic Dependency","media_type":"text/html"},{"type":"related_material","path":"/posts/arcee-open-model-science-post-training/","reason":"Shares open models and post training.","url":"https://newruntime.com/posts/arcee-open-model-science-post-training/","title":"Arcee Turns Scientific Post-Training Into A Run Ledger","media_type":"text/html"}]}