AWS Certified Machine Learning – Specialty — Question 331
A tourism company uses a machine learning (ML) model to make recommendations to customers. The company uses an Amazon SageMaker environment and set hyperparameter tuning completion criteria to MaxNumberOfTrainingJobs.
An ML specialist wants to change the hyperparameter tuning completion criteria. The ML specialist wants to stop tuning immediately after an internal algorithm determines that tuning job is unlikely to improve more than 1% over the objective metric from the best training job.
Which completion criteria will meet this requirement?
Answer options
- A. MaxRuntimeInSeconds
- B. TargetObjectiveMetricValue
- C. CompleteOnConvergence
- D. MaxNumberOfTrainingJobsNotImproving
Correct answer: C
Explanation
The CompleteOnConvergence setting in Amazon SageMaker hyperparameter tuning stops the tuning job when the optimization algorithm determines that further iterations will not improve the objective metric by more than 1%. Other parameters like MaxRuntimeInSeconds and TargetObjectiveMetricValue stop jobs based on time limits or reaching a specific metric goal, respectively, rather than convergence behavior.