SIENTIAPDE-1645: Expose detailed model training information via a new Prometheus gauge. This gauge, sientia_training_info, records metadata such as dataset sizes, feature count, and evaluation metrics (MSE, MAE, R2) along with the training run's timestamp.

This commit is contained in:
vitor-aignosi
2026-06-18 09:56:30 -03:00
parent bc65ebb955
commit 2c63414770
3 changed files with 76 additions and 0 deletions

View File

@@ -27,6 +27,22 @@ APP_UP = Gauge(
_TRAINING_LABELS = ['pod_id', 'model_name', 'model_type']
SIENTIA_TRAINING_INFO = Gauge(
'sientia_training_info',
'Metadata and execution timestamp (ms) of the last successful model training run',
[
'pod_id',
'model_name',
'model_type',
'dataset_train_rows',
'dataset_val_rows',
'feature_count',
'mse',
'mae',
'r2',
],
)
SIENTIA_TRAINING_MODEL_TRAINED_TOTAL = Counter(
'sientia_training_model_trained_total',
'Number of successfully completed model training runs',