AWS bedrock documentation change
Summary
Removed all references to 'continued pre-training' customization method throughout the documentation. Updated headings, instructions, and API references to focus exclusively on fine-tuning. Modified hyperlinks to point to fine-tuning-specific preparation guides.
Security assessment
The changes involve removing deprecated features (continued pre-training) without any mention of security vulnerabilities, exploits, or weaknesses. No security advisories, vulnerability fixes, or security enhancements are referenced. The modifications appear to be product feature updates rather than security-related changes.
Diff
diff --git a/bedrock/latest/userguide/model-customization-submit.md b/bedrock/latest/userguide/model-customization-submit.md index 5af42eea9..d63ed8dc8 100644 --- a//bedrock/latest/userguide/model-customization-submit.md +++ b//bedrock/latest/userguide/model-customization-submit.md @@ -7 +7 @@ PrerequisitesSubmit your job -# Submit a model customization job for fine-tuning or continued pre-training +# Submit a model customization job for fine-tuning @@ -9 +9 @@ PrerequisitesSubmit your job -You can create a custom model by using Fine-tuning or Continued Pre-training in the Amazon Bedrock console or API. You can further fine tune an existing custom model. The customization job can take several hours. The duration of the job depends on the size of the training data (number of records, input tokens, and output tokens), number of epochs, and batch size. +You can create a custom model by using fine-tuning in the Amazon Bedrock console or API. You can further fine tune an existing custom model. The customization job can take several hours. The duration of the job depends on the size of the training data (number of records, input tokens, and output tokens), number of epochs, and batch size. @@ -35 +35 @@ To submit a model customization job in the console, carry out the following step - 3. In the **Models** tab, choose **Customize model** and then **Create Fine-tuning job** or **Create Continued Pre-training job** , depending on the type of model you want to train. + 3. In the **Models** tab, choose **Customize model** and then **Create Fine-tuning job**. @@ -65 +65 @@ If you include a VPC configuration, the console cannot create a new service role - 11. Choose **Fine-tune model** or **Create Continued Pre-training job** to begin the job. + 11. Choose **Fine-tune model** to begin the job. @@ -91 +91 @@ If you include a `vpcConfig` field, make sure that the role has the proper permi - * `trainingDataConfig` – An object containing the Amazon S3 URI of the training dataset. Depending on the customization method and model, you can also include a `validationDataConfig`. For more information about preparing the datasets, see [Prepare your training datasets for fine-tuning and continued pre-training](./model-customization-prepare.html). + * `trainingDataConfig` – An object containing the Amazon S3 URI of the training dataset. Depending on the customization method and model, you can also include a `validationDataConfig`. For more information about preparing the datasets, see [Prepare data for fine-tuning your models](./model-customization-prepare.html). @@ -127 +127 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Meta Llama 3.2 models +Custom model hyperparameters