The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
# ================================================================================
# ================================= CORE METRICS =================================
# ================================================================================
===== FINAL SUMMARY =====
Best epoch : 1
Train accuracy : 0.762000
Val accuracy : 0.762667
Train loss : 0.162137
Val loss : 0.158374
Threshold : 0.570000
Test accuracy : 0.740000
Test loss : 0.571433 ===== TRAIN =====
Classification Report| precision | recall | f1-score | support | |
|---|---|---|---|---|
| 0 | 0.781282 | 0.955224 | 0.859541 | 2412.000000 |
| 1 | 0.803993 | 0.407169 | 0.540574 | 1088.000000 |
| accuracy | 0.784857 | 0.784857 | 0.784857 | 3500.000000 |
| macro avg | 0.792637 | 0.681196 | 0.700057 | 3500.000000 |
| weighted avg | 0.788342 | 0.784857 | 0.760388 | 3500.000000 |
| Positive (1) | Negative (0) | |
|---|---|---|
| Positive (1) | 443 | 108 |
| Negative (0) | 645 | 2304 |
AUC/AUPRC AUC (ROC): 0.833371 AUPRC: 0.721644
===== VALIDATION =====
Classification Report| precision | recall | f1-score | support | |
|---|---|---|---|---|
| 0 | 0.742188 | 0.969388 | 0.840708 | 490.000000 |
| 1 | 0.863636 | 0.365385 | 0.513514 | 260.000000 |
| accuracy | 0.760000 | 0.760000 | 0.760000 | 750.000000 |
| macro avg | 0.802912 | 0.667386 | 0.677111 | 750.000000 |
| weighted avg | 0.784290 | 0.760000 | 0.727281 | 750.000000 |
| Positive (1) | Negative (0) | |
|---|---|---|
| Positive (1) | 95 | 15 |
| Negative (0) | 165 | 475 |
AUC/AUPRC AUC (ROC): 0.856888 AUPRC: 0.767956
===== TEST =====
Classification Report| precision | recall | f1-score | support | |
|---|---|---|---|---|
| 0 | 0.780031 | 0.943396 | 0.853971 | 530.000000 |
| 1 | 0.724771 | 0.359091 | 0.480243 | 220.000000 |
| accuracy | 0.772000 | 0.772000 | 0.772000 | 750.000000 |
| macro avg | 0.752401 | 0.651244 | 0.667107 | 750.000000 |
| weighted avg | 0.763821 | 0.772000 | 0.744344 | 750.000000 |
| Positive (1) | Negative (0) | |
|---|---|---|
| Positive (1) | 79 | 30 |
| Negative (0) | 141 | 500 |
AUC/AUPRC AUC (ROC): 0.801844 AUPRC: 0.644767
Scenario D emits three structured log tables that document ensemble behavior and make the MAIN vs TEMP workflow auditable and reproducible.
Main Log (main_log) —
Iteration-level snapshots of the Primary (MAIN) ensemble state and
evaluation results under the selected metric.
Movement Log (movement_log) —
Deterministic promotion and replacement events between TEMP and MAIN
(what moved, directionality, and why).
Change Log (change_log) —
Per-iteration update diagnostics and structural deltas recorded during
training and selection steps.
These tables are returned in res_D$runs[[1]]$tables.
The previews below are capped for vignette readability.
| serial | iteration | phase | metric_name | metric_value | message | timestamp |
|---|---|---|---|---|---|---|
| 0.0.1 | 1 | main_before | accuracy | 0.5386667 | 2026-02-24 09:50:38 | |
| 0.0.2 | 1 | main_before | accuracy | 0.6933333 | 2026-02-24 09:50:38 | |
| 0.0.1 | 1 | main_after | accuracy | 0.6693333 | 2026-02-24 09:50:45 | |
| 0.0.2 | 1 | main_after | accuracy | 0.8160000 | 2026-02-24 09:50:45 | |
| 0.0.1 | 2 | main_before | accuracy | 0.6693333 | 2026-02-24 09:50:45 | |
| 0.0.2 | 2 | main_before | accuracy | 0.8160000 | 2026-02-24 09:50:45 | |
| 0.0.1 | 2 | main_after | accuracy | 0.6693333 | 2026-02-24 09:50:52 | |
| 0.0.2 | 2 | main_after | accuracy | 0.8160000 | 2026-02-24 09:50:52 |
| serial | iteration | message | timestamp |
|---|---|---|---|
| 0.0.1 | 1 | removed (no replacement) | 2026-02-24 09:50:45 |
| 0.0.1 | 2 | removed (no replacement) | 2026-02-24 09:50:52 |
| serial | iteration | message | timestamp |
|---|---|---|---|
| 0.0.1 | 1 | model removed from main | 2026-02-24 09:50:45 |
| 0.0.1 | 2 | model removed from main | 2026-02-24 09:50:52 |
Note: Tables below are preview-capped for vignette
readability. Full tables remain available in res_D\(runs[[1]]\)tables. Artifact writing
is OFF by default for CRAN-safety.
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.