A governed fine‑tune for $0.86: Qwen3‑4B on IFC/BIM, with a person approving every step
说明与用途
使用cairn控制平面对Qwen3‑4B在IFC/BIM数据上的微调进行治理,成本仅$0.86,测试损失降低89%,并保持了通用能力。
问题
Fine‑tuning a model is easy to start, but running it responsibly in a team is hard: no spend approval, no data record, and no objective comparison to the base model.
结果
The fine‑tune ran for 73 minutes on a single T4, cost $0.86, reduced test loss from 1.955 to 0.218, and showed no measurable degradation on standard benchmarks.
工作流
- Prepare dataset with approval and deduplication
- Approve run after cost and data checks
- Acquire GPU instance and run smoke test
- Train for 353 steps with checkpoints every 50 steps
- Release GPU instance after training
- Compare candidate to base model on held‑out data
- Promote model after approval
证据
Fine‑tuning a model is easy to start. Running it responsibly in a team is the hard part.
The adapter, the dataset, the training curve and the raw eval results are public: cairndev/qwen3-4b-ifc-bim-qlora and cairndev/ifc-bim-alpaca-dedup.
The run then paused at promote-model, with the losses on the card. Promotion is a decision, not a side effect.
- 记录日期: 2026-10-27T00:11:29.128Z