Experiment · sql

Controlled SQL LoRA rank sweep

Hyperparameter sweeps are valid only inside one frozen experiment contract; they are not project-completion chores. Retained outcome: rejected.

Outcome
rejected
Family
sql
Evidence confidence
exact
Record
training run

Evidence readout

no controlled sweep was run because no next target/eval was frozen after the confounded historical comparisons

What the attempt taught

Hyperparameter sweeps are valid only inside one frozen experiment contract; they are not project-completion chores.

Why it stopped or stayed bounded

Without one active frozen recipe, a rank sweep would measure a new arbitrary setup rather than resolve the historical confound.

Method and scope

  • Experiment family: sql.
  • Record kind: training run.
  • Objective: rank sensitivity.
  • Methods: lora.
  • Base models: qwen3-0.6b.

Disposition

Closed for this project. Any future rank study begins as a new experiment with fixed data, seed, steps, learning rate, and eval.

This retained disposition is historical evidence, not authorization to restart the experiment. A new run needs a fresh question, frozen evaluator, explicit resource budget, and scoped tracking issue.

How to read this dossier

This canonical page separates the retained repository decision from the material that informed it. A source may describe an external claim, historical measurement, local observation, or planned procedure; those evidence classes are not interchangeable. Follow the provenance links before reusing a number or method.

Status and disposition describe what PostTrainLLM retained when this record was indexed. They are not a live product promise, a newly run benchmark, or permission to restart historical work. Unknown or unmeasured fields remain unknown rather than being treated as zero.

To reuse the record, first name the exact claim you need and trace it to the linked source. Then check whether the original environment, model revision, data split, evaluator, hardware, and budget match the proposed use. If they do not, treat the record as a hypothesis or design reference and run the smallest fresh comparison that can falsify it. Preserve negative outcomes and regressions beside any improvement; a local win on one slice does not silently become a general capability claim.

Source provenance

The normalized record comes from docs/attempts.json. The links below are the tracked evidence and explanatory sources preserved with the record.