Home / example runs
Red wine quality (OpenML 40691)
1599 wines, 11 physico-chemical measurements, predict the sensory quality score.
Pre-computed on 2026-11-09 18:20 UTC on a developer laptop (Windows 11), CPU only. Scripted planner, no LLM, no network
calls during the run. Dataset: OpenML 40691.
- Task
- regression, target
quality, metricrmse, 1599 rows x 12 columns - Status
- done
- Chosen model
rf- Validation rmse
- 0.5802
- Reviewer verdict
- APPROVE
- Columns dropped for leakage
- none
- Steps
- 13
- Wall time
- 34.8 s (process start to report); agent clock 31.8 s. One run on a shared machine that was busy with other jobs: a timing sample, not a benchmark.
- Budgets
- soft wall 55 s (agent stops searching), hard limit 90 s (process killed), FLAML 15 s, 3 tuning trials
Agent steps
| # | tool | server | ok | latency (s) |
|---|---|---|---|---|
| 0 | profile_dataset | data-tools | yes | 0.11 |
| 1 | detect_leakage | data-tools | yes | 3.89 |
| 2 | decide_leakage | agent | yes | 0.00 |
| 3 | train_model | experiments | yes | 0.06 |
| 4 | train_model | experiments | yes | 0.11 |
| 5 | train_model | experiments | yes | 0.75 |
| 6 | train_model | experiments | yes | 3.77 |
| 7 | tune_model | experiments | yes | 3.05 |
| 8 | train_model | experiments | yes | 17.02 |
| 9 | compare_models | experiments | yes | 0.09 |
| 10 | review | agent | yes | 0.00 |
| 11 | explain_model | experiments | yes | 2.75 |
| 12 | report | agent | yes | 0.00 |