AWS bedrock documentation change
Summary
Added CloudWatch Logs integration details and dataset validation guidance for distillation jobs
Security assessment
The changes explain operational logging features and data preparation steps without introducing security controls or addressing vulnerabilities. The validation aspect appears focused on data structure rather than security.
Diff
diff --git a/bedrock/latest/userguide/distillation-data-prep-option-2.md b/bedrock/latest/userguide/distillation-data-prep-option-2.md index 409468848..7f1112f68 100644 --- a//bedrock/latest/userguide/distillation-data-prep-option-2.md +++ b//bedrock/latest/userguide/distillation-data-prep-option-2.md @@ -5 +5 @@ -Add request metadata to prompts and responses +Add request metadata to prompts and responsesValidate your dataset @@ -8,0 +9,2 @@ Add request metadata to prompts and responses +When you create a distillation job, you can have Amazon Bedrock use existing teacher responses from CloudWatch Logs invocation logs as training data. For Amazon Bedrock, an invocation log is a detailed record of model invocations. + @@ -97,0 +100,4 @@ You can specify the invocation log as your input data source and what filters to +## Validate your dataset + +Before you run your distillation job, you can validate your input dataset using a [Python script](https://github.com/aws-samples/amazon-bedrock-samples/blob/main/custom-models/model_distillation/dataset-validation/README.md). +