gitea_admin/sientia-dataops-model-manager
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SIENTIAPDE-1309: Update README with Helm instructions and refactor experiment status messages. Also, update values.yaml with new image and configurations.

Browse Source
This commit is contained in:
Bruno Domingues
2025-11-06 15:34:03 -03:00
parent a625ef6c19
commit c7f44a2423
9 changed files with 133 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
model_manager/utils/models/experiment_status.py
View File

@@ -15,20 +15,20 @@ class ExperimentStatus(str, Enum):
Attributes:
ORCHESTRATOR_VALIDATION_ERROR: Error in the parameters validation.
MAGE_WAITING_PROC: Initial status indicating experiment is registered and waiting for processing.
ORCHESTRATOR_WAITING_PROC: Initial status indicating experiment is registered and waiting for processing.
TRAINING_SUCCESS: Training completed successfully with model and metrics calculated.
TRAINING_ERROR: Training failed due to data issues, model errors, or other exceptions.
MLFLOW_SENT: Model successfully saved to MLFlow.
MLFLOW_SEND_ERROR: Model saving to MLFlow failed due to connection or serialization errors.
TRACKING_SENT: Model successfully saved to MLFlow.
TRACKING_SEND_ERROR: Model saving to MLFlow failed due to connection or serialization errors.
FILE_DELETED: Cleanup completed successfully with all artifacts removed.
FILE_DELETE_ERROR: Cleanup failed due to file system or MinIO errors.
"""
ORCHESTRATOR_VALIDATION_ERROR = 'ORCHESTRATOR_VALIDATION_ERROR'
MAGE_WAITING_PROC = 'MAGE_WAITING_PROC'
ORCHESTRATOR_WAITING_PROC = 'ORCHESTRATOR_WAITING_PROC'
TRAINING_SUCCESS = 'TRAINING_SUCCESS'
TRAINING_ERROR = 'TRAINING_ERROR'
MLFLOW_SENT = 'MLFLOW_SENT'
MLFLOW_SEND_ERROR = 'MLFLOW_SEND_ERROR'
TRACKING_SENT = 'TRACKING_SENT'
TRACKING_SEND_ERROR = 'TRACKING_SEND_ERROR'
FILE_DELETED = 'FILE_DELETED'
FILE_DELETE_ERROR = 'FILE_DELETE_ERROR'

8
model_manager/workflows/train_model.py
View File

@@ -163,7 +163,7 @@ class TrainModel:
Validate and convert training parameters from dict to TrainModelParams.
This method calls the validate_train_params activity to convert and validate
the input parameters. On success, updates DB status to MAGE_WAITING_PROC.
the input parameters. On success, updates DB status to ORCHESTRATOR_WAITING_PROC.
On error, updates DB status to ORCHESTRATOR_VALIDATION_ERROR.
Args:
@@ -192,7 +192,7 @@ class TrainModel:
metadata=metadata,
experiment_run_id=experiment_run_id,
update_type=UpdateType.STATUS,
status=ExperimentStatus.MAGE_WAITING_PROC,
status=ExperimentStatus.ORCHESTRATOR_WAITING_PROC,
)
return train_params
@@ -246,7 +246,7 @@ class TrainModel:
metadata=metadata,
experiment_run_id=experiment_run_id,
update_type=UpdateType.MODEL_SAVED,
status=ExperimentStatus.MLFLOW_SENT,
status=ExperimentStatus.TRACKING_SENT,
run_name=train_result.get('run_name'),
)
@@ -260,7 +260,7 @@ class TrainModel:
status = ExperimentStatus.TRAINING_ERROR
if isinstance(e, ModelTrainingError) and (e.model_trained and not e.model_saved):
status = ExperimentStatus.MLFLOW_SEND_ERROR
status = ExperimentStatus.TRACKING_SEND_ERROR
await self._update_experiment_run(
metadata=metadata,