This indicates that the algorithm thinks it has been passed bad data. Perhaps a problem with your splitting?
I would suggest two things:
- Try running the algorithm on the original data using the
"BatchStrategy": "MultiRecord"arguments and see if you have better luck.
- Look in the cloudwatch logs for your run and see if there's any helpful information about what the algorithm didn't like. You can find these in the log group "/aws/sagemaker/TransformJobs" in the log stream that begins with your job name.
Sagemaker batch transformAccepted Answer
xgboost sagemaker batch transform job output in multiple linesAccepted Answerasked 2 years ago
SageMaker Batch Transform local mode?Accepted AnswerEXPERTasked 3 years ago
Is there a way to automate failure handling and retries when using Amazon SageMaker batch transform?Accepted AnswerEXPERTasked 2 years ago
Sagemaker Pipelines - Batch Transform job using generated predictions as input for the modelasked 4 months ago
How to pass null/Nan values into the dataframe passed into batch transformasked 4 years ago
Load balancing is not happening on sagemaker batch transform jobasked 7 months ago
Sagemaker batch transform 415 errorAccepted Answer
SageMaker XGBoost batch transform AttributeErrorasked 3 months ago
InternalServerError with SageMaker Batch transform jobasked 2 months ago