Kumo.ai home page
Search...
⌘K
Ask AI
Community
Contact Support
Start for free
Start for free
Search...
Navigation
Training Job Plan
tune_metric
Guide
Examples
Reference
FAQ
Releases
Predictive Query
Overview
Primary Commands
Aggregation Operators
Boolean Operators
Model Plan
Column Processing
Model Architecture
Neighbor Sampling
Optimization
Training Job Plan
refit_full
refit_trainval
metrics
num_experiments
tune_metric
Training Table Generation
SDK
SDK Reference
On this page
tune_metric: (auroc, acc, mae, f1, loss, ap_macro) (Optional)
Description
Supported Task Types
Default Values
Training Job Plan
tune_metric
tune_metric: (auroc, acc, mae, f1, loss, ap_macro)
(Optional)
Description
Specifies a metric that you want AutoML to use for optimizing training experiments.
The tune metric needs to be present in the list of metrics in the model plan.
The tune metric is used for early stopping and model selection.
For available metrics, please refer to
Kumo Evaluation Metrics
.
Supported Task Types
All
Default Values
run_mode
Default Value
FAST
Inferred
NORMAL
Inferred
BEST
Inferred
num_experiments
end_time
Assistant
Responses are generated using AI and may contain mistakes.