Models - Aug 4, 2026

SageMaker Model Customization Data and Evaluation Guide

Quick answer

SageMaker model customization uses datasets and evaluators as versioned assets. AWS describes training examples such as prompt-response pairs, domain text, or labeled data. Evaluators can be:

  • code-based reward functions, used for verifiable scoring and custom scorers;
  • natural-language reward prompts, used for RLAIF and LLM-as-a-judge evaluation.

Keep training, validation, and final holdout data separate. A scorer that influenced training cannot provide an independent deployment decision by itself.

Dataset contract

For every dataset version, record:

  1. source, owner, license, consent, and allowed purpose;
  2. collection window and population;
  3. schema, task type, and expected output;
  4. deduplication and contamination checks;
  5. sensitive-data detection and redaction;
  6. train, validation, and holdout split method;
  7. known gaps, label quality, and removal process.

Do not place secrets or unrelated personal data in training examples. Confirm S3, KMS, IAM, account, and Region boundaries before upload.

Evaluator contract

EvaluatorGood fitRequired check
Exact or code scorerStructured, testable outcomesEdge cases, gaming, deterministic behavior
Domain rubricMulti-dimensional qualityReviewer agreement and rubric coverage
LLM judgeScalable qualitative comparisonBias, prompt sensitivity, position effects, calibration
Human reviewHigh-impact or ambiguous outputsExpertise, sampling, privacy, and escalation

Use more than one signal. A reward function can be incomplete, a reward prompt can prefer fluent errors, and humans can disagree. Inspect false positives and false negatives against an expert-reviewed sample.

Evaluation and lineage

AWS documents logged models, registered models, model package groups, and automatically captured lineage between jobs, input datasets, output models, evaluations, and deployments. Registration supports governance; it does not itself approve the model.

Compare the custom model with its base model on task quality, regressions, safety, latency, throughput, and cost. Define a rejection threshold before looking at final results. If an evaluation feature uses Amazon Bedrock Evaluations, review AWS’s note about possible cross-Region processing within the same geography.

Use the setup guide for job submission and the deployment guide after approval.

Frequently asked questions

What are SageMaker model customization assets?

AWS defines datasets and evaluators as model customization assets. Datasets provide training or evaluation examples, while evaluators use reward functions or reward prompts to assess outputs.

What is the difference between a reward function and a reward prompt?

A reward function is code-based scoring logic, while a reward prompt instructs an LLM to judge response quality. Both require validation and neither should be treated as unquestionable ground truth.

Does a successful customization job mean the model passed evaluation?

No. Job completion creates artifacts and logged-model records. Evaluation on an untouched holdout plus human and deployment-specific review is a separate approval step.

Official sources

Source check: August 4, 2026. Verify supported dataset formats, scorer interfaces, processing locations, permissions, lineage behavior, and evaluation limits before use.