Adapt a model with internal classification data.
Measure performance independently after adaptation.
Choose two appropriate practices.
Separate adaptation and evaluation data without entity overlap, and include production boundary and safety examples in the held-out set.
Detailed explanation
Generalization cannot be measured if the same data is reused.
Generalization cannot be measured if the same data is reused.
The evaluation reflects real risks.
The evaluation reflects real risks.
Overfitting is hidden.
Overfitting is hidden.
The held-out set is no longer independent.
The held-out set is no longer independent.
Try it yourself
An example you can run in a temporary verification environment.
Amazon Bedrock公式モデルカスタマイズとAIF-C01 Domain 3.1・3.3を確認する。Expected result
適応データと独立評価データの分離理由を説明できる。Key points
- Adaptation
- Independent evaluation
- Boundary cases
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.