junior-ml-dev

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, metric rmse, 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

#toolserveroklatency (s)
0profile_datasetdata-toolsyes0.11
1detect_leakagedata-toolsyes3.89
2decide_leakageagentyes0.00
3train_modelexperimentsyes0.06
4train_modelexperimentsyes0.11
5train_modelexperimentsyes0.75
6train_modelexperimentsyes3.77
7tune_modelexperimentsyes3.05
8train_modelexperimentsyes17.02
9compare_modelsexperimentsyes0.09
10reviewagentyes0.00
11explain_modelexperimentsyes2.75
12reportagentyes0.00

The agent's own report

Open the report on its own page.