AWS bedrock documentation change
Summary
Clarified Test in Playground requirements, removed redundant Provisioned Throughput section, and improved wording about model evaluation benefits
Security assessment
Changes focus on usability improvements and content reorganization without addressing security mechanisms or vulnerabilities. The added inference setup requirement clarification is operational rather than security-related.
Diff
diff --git a/bedrock/latest/userguide/rft-evaluate-model.md b/bedrock/latest/userguide/rft-evaluate-model.md index a17ea75a8..87610221a 100644 --- a//bedrock/latest/userguide/rft-evaluate-model.md +++ b//bedrock/latest/userguide/rft-evaluate-model.md @@ -39 +39,3 @@ If you upload a validation dataset, you will see two additional graphs in traini -Use the Test in Playground feature for quick, ad-hoc evaluations. This interactive tool allows you to: +Use the Test in Playground feature for quick, ad-hoc evaluations. To use the Test in Playground feature, inference needs to be set up. For more information, see Setting up inference for evaluation. + +This interactive tool allows you to: @@ -52,2 +53,0 @@ Use the Test in Playground feature for quick, ad-hoc evaluations. This interacti -To use the Test in Playground feature, inference needs to be set up. For more information, see Setting up inference for evaluation. - @@ -56 +56 @@ To use the Test in Playground feature, inference needs to be set up. For more in -Use Amazon Bedrock's Model Evaluation to assess your RFT model using your own datasets. This provides comprehensive performance analysis with standardized metrics and benchmarks. Here are some example of the Bedrock Model Evaluation benefits. +Use Amazon Bedrock's Model Evaluation to assess your RFT model using your own datasets. This provides comprehensive performance analysis with standardized metrics and benchmarks. Here are some examples of the Amazon Bedrock Model Evaluation benefits. @@ -71 +71 @@ Use Amazon Bedrock's Model Evaluation to assess your RFT model using your own da -Before evaluating your RFT model, set up inference using one of these options. +Before evaluating your RFT model, set up inference using one of these options: @@ -77,4 +76,0 @@ Create a custom model on-demand deployment for flexible, pay-per-use evaluation. -### Provisioned Throughput - -For mission-critical workloads or extensive evaluation requirements, purchase Provisioned Throughput by Tokens (PTv2). This option allows you to provision input and output tokens-per-minute (TPM) throughput for consistent performance. -