AWS nova documentation change
Summary
Expanded fine-tuning documentation with detailed steps, model list updates, and security configuration guidance
Security assessment
Added explicit guidance about encryption and VPC configuration as part of security best practices, but not tied to a specific security issue
Diff
diff --git a/nova/latest/userguide/customize-fine-tune.md b/nova/latest/userguide/customize-fine-tune.md index fa05beb87..2e737fb99 100644 --- a//nova/latest/userguide/customize-fine-tune.md +++ b//nova/latest/userguide/customize-fine-tune.md @@ -5 +5 @@ -Available models +Available modelsPerforming custom fine-tuning @@ -26 +26 @@ You can customize the Amazon Nova models using the [_fine-tuning_ method](https: - * [Performing custom fine-tuning](./customize-fine-tune-steps.html) + * Performing custom fine-tuning @@ -30 +30,3 @@ You can customize the Amazon Nova models using the [_fine-tuning_ method](https: - * [Guidelines for preparing your data for Amazon Nova](./customize-fine-tune-prepare.html) + * [Preparing data for fine-tuning Understanding models](./fine-tune-prepare-data-understanding.html) + + * [Preparing data for fine-tuning Creative Content Generation models](./fine-tune-prepare-data-creative-content.html) @@ -39 +41,37 @@ You can customize the Amazon Nova models using the [_fine-tuning_ method](https: -Fine-tuning is available for Amazon Nova Micro, Lite, and Pro understanding models and their supported text, image, and video modalities. +Fine-tuning is available for the following Amazon Nova models and their supported text, image, and video modalities. + + * Amazon Nova Micro + + * Amazon Nova Lite + + * Amazon Nova Pro + + * Amazon Nova Canvas + + + + +## Performing custom fine-tuning + +To perform custom fine-tuning with Amazon Nova models, you do the following: + + 1. Create a training dataset and a validation dataset (if applicable) for your customization task. For more information about preparing data, see the following: + + * [Preparing data for fine-tuning Understanding models](./fine-tune-prepare-data-understanding.html) + + * [Preparing data for fine-tuning Creative Content Generation models](./fine-tune-prepare-data-creative-content.html) + + 2. If you plan to use a new custom IAM role, follow the instructions in [Create a service role for model customization](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-iam-role.html) to create an IAM role with access to your data in Amazon S3 buckets. Or you can use an existing role or let the console automatically create a role with the proper permissions. + + 3. (Optional) Configure [Encryption of Amazon Nova model customization jobs and artifacts](./customize-fine-tune-encrypt.html), [VPC](https://docs.aws.amazon.com/bedrock/latest/userguide/vpc-model-customization.html), or both, for extra security. + + 4. [Create a Fine-tuning job](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-submit.html), controlling the training process by adjusting the [hyperparameter](./customize-fine-tune-hyperparameters.html) values. + + 5. [Analyze the results](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-analyze.html) by looking at the training or validation metrics or by using model evaluation. + + 6. [Purchase Provisioned Throughput](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html) for your newly created custom model. + + 7. [Use your custom model](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html) as you would a base model in Amazon Bedrock tasks, such as model inference. + + + @@ -49 +87 @@ Customizing models -Performing custom fine-tuning +Encrypting jobs and artifacts