mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2025-11-02 02:41:00 +00:00
04_optional-aws-sagemaker-notebook (#451)
* 04_optional-aws-sagemaker-notebook * Update setup/04_optional-aws-sagemaker-notebook/cloudformation-template.yml * Update README.md --------- Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
This commit is contained in:
rvaneijk
GitHub
parent
37aed8fc2c
commit
f936ad4b4e
31
setup/04_optional-aws-sagemaker-notebook/README.md
Normal file
31
setup/04_optional-aws-sagemaker-notebook/README.md
Normal file
@ -0,0 +1,31 @@
|
||||
# AWS CloudFormation Template: Jupyter Notebook with LLMs-from-scratch Repo
|
||||
|
||||
This CloudFormation template creates a GPU-enabled Jupyter notebook in Amazon SageMaker with an execution role and the LLMs-from-scratch GitHub repository.
|
||||
|
||||
## What it does:
|
||||
|
||||
1. Creates an IAM role with the necessary permissions for the SageMaker notebook instance.
|
||||
2. Creates a KMS key and an alias for encrypting the notebook instance.
|
||||
3. Configures a notebook instance lifecycle configuration script that:
|
||||
- Installs a separate Miniconda installation in the user's home directory.
|
||||
- Creates a custom Python environment with TensorFlow 2.15.0 and PyTorch 2.1.0, both with CUDA support.
|
||||
- Installs additional packages like Jupyter Lab, Matplotlib, and other useful libraries.
|
||||
- Registers the custom environment as a Jupyter kernel.
|
||||
4. Creates the SageMaker notebook instance with the specified configuration, including the GPU-enabled instance type, the execution role, and the default code repository.
|
||||
|
||||
## How to use:
|
||||
|
||||
1. Download the CloudFormation template file (`cloudformation-template.yml`).
|
||||
2. In the AWS Management Console, navigate to the CloudFormation service.
|
||||
3. Create a new stack and upload the template file.
|
||||
4. Provide a name for the notebook instance (e.g., "LLMsFromScratchNotebook") (defaults to the LLMs-from-scratch GitHub repo).
|
||||
5. Review and accept the template's parameters, then create the stack.
|
||||
6. Once the stack creation is complete, the SageMaker notebook instance will be available in the SageMaker console.
|
||||
7. Open the notebook instance and start using the pre-configured environment to work on your LLMs-from-scratch projects.
|
||||
|
||||
## Key Points:
|
||||
|
||||
- The template creates a GPU-enabled (`ml.g4dn.xlarge`) notebook instance with 50GB of storage.
|
||||
- It sets up a custom Miniconda environment with TensorFlow 2.15.0 and PyTorch 2.1.0, both with CUDA support.
|
||||
- The custom environment is registered as a Jupyter kernel, making it available for use in the notebook.
|
||||
- The template also creates a KMS key for encrypting the notebook instance and an IAM role with the necessary permissions.
|
||||
167
setup/04_optional-aws-sagemaker-notebook/cloudformation-template.yml
Executable file
167
setup/04_optional-aws-sagemaker-notebook/cloudformation-template.yml
Executable file
@ -0,0 +1,167 @@
|
||||
AWSTemplateFormatVersion: '2010-09-09'
|
||||
Description: 'CloudFormation template to create a GPU-enabled Jupyter notebook in SageMaker with an execution role and
|
||||
LLMs-from-scratch Repo'
|
||||
|
||||
Parameters:
|
||||
NotebookName:
|
||||
Type: String
|
||||
Default: 'LLMsFromScratchNotebook'
|
||||
DefaultRepoUrl:
|
||||
Type: String
|
||||
Default: 'https://github.com/rasbt/LLMs-from-scratch.git'
|
||||
|
||||
Resources:
|
||||
SageMakerExecutionRole:
|
||||
Type: AWS::IAM::Role
|
||||
Properties:
|
||||
AssumeRolePolicyDocument:
|
||||
Version: '2012-10-17'
|
||||
Statement:
|
||||
- Effect: Allow
|
||||
Principal:
|
||||
Service:
|
||||
- sagemaker.amazonaws.com
|
||||
Action:
|
||||
- sts:AssumeRole
|
||||
ManagedPolicyArns:
|
||||
- arn:aws:iam::aws:policy/AmazonSageMakerFullAccess
|
||||
- arn:aws:iam::aws:policy/AmazonBedrockFullAccess
|
||||
|
||||
KmsKey:
|
||||
Type: AWS::KMS::Key
|
||||
Properties:
|
||||
Description: 'KMS key for SageMaker notebook'
|
||||
KeyPolicy:
|
||||
Version: '2012-10-17'
|
||||
Statement:
|
||||
- Effect: Allow
|
||||
Principal:
|
||||
AWS: !Sub 'arn:aws:iam::${AWS::AccountId}:root'
|
||||
Action: 'kms:*'
|
||||
Resource: '*'
|
||||
EnableKeyRotation: true
|
||||
|
||||
KmsKeyAlias:
|
||||
Type: AWS::KMS::Alias
|
||||
Properties:
|
||||
AliasName: !Sub 'alias/${NotebookName}-kms-key'
|
||||
TargetKeyId: !Ref KmsKey
|
||||
|
||||
TensorConfigLifecycle:
|
||||
Type: AWS::SageMaker::NotebookInstanceLifecycleConfig
|
||||
Properties:
|
||||
NotebookInstanceLifecycleConfigName: "TensorConfigv241128"
|
||||
OnCreate:
|
||||
- Content: !Base64 |
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Create a startup script that will run in the background
|
||||
cat << 'EOF' > /home/ec2-user/SageMaker/setup-environment.sh
|
||||
#!/bin/bash
|
||||
|
||||
sudo -u ec2-user -i <<'INNEREOF'
|
||||
unset SUDO_UID
|
||||
|
||||
# Install a separate conda installation via Miniconda
|
||||
WORKING_DIR=/home/ec2-user/SageMaker/custom-miniconda
|
||||
mkdir -p "$WORKING_DIR"
|
||||
wget https://repo.anaconda.com/miniconda/Miniconda3-4.7.12.1-Linux-x86_64.sh -O "$WORKING_DIR/miniconda.sh"
|
||||
bash "$WORKING_DIR/miniconda.sh" -b -u -p "$WORKING_DIR/miniconda"
|
||||
rm -rf "$WORKING_DIR/miniconda.sh"
|
||||
|
||||
# Ensure we're using the Miniconda conda
|
||||
export PATH="$WORKING_DIR/miniconda/bin:$PATH"
|
||||
|
||||
# Initialize conda
|
||||
"$WORKING_DIR/miniconda/bin/conda" init bash
|
||||
source ~/.bashrc
|
||||
|
||||
# Create and activate environment
|
||||
KERNEL_NAME="tensorflow2_p39"
|
||||
PYTHON="3.9"
|
||||
"$WORKING_DIR/miniconda/bin/conda" create --yes --name "$KERNEL_NAME" python="$PYTHON"
|
||||
eval "$("$WORKING_DIR/miniconda/bin/conda" shell.bash activate "$KERNEL_NAME")"
|
||||
|
||||
# Install CUDA toolkit and cuDNN
|
||||
"$WORKING_DIR/miniconda/bin/conda" install --yes cudatoolkit=11.8 cudnn
|
||||
|
||||
# Install ipykernel
|
||||
"$WORKING_DIR/miniconda/envs/$KERNEL_NAME/bin/pip" install --quiet ipykernel
|
||||
|
||||
# Install PyTorch with CUDA support
|
||||
"$WORKING_DIR/miniconda/envs/$KERNEL_NAME/bin/pip3" install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
|
||||
|
||||
# Install other packages
|
||||
"$WORKING_DIR/miniconda/envs/tensorflow2_p39/bin/pip" install tensorflow[gpu]
|
||||
"$WORKING_DIR/miniconda/bin/conda" install --yes tensorflow-gpu
|
||||
"$WORKING_DIR/miniconda/envs/tensorflow2_p39/bin/pip" install tensorflow==2.15.0
|
||||
"$WORKING_DIR/miniconda/bin/conda" install --yes setuptools tiktoken tqdm numpy pandas psutil
|
||||
|
||||
"$WORKING_DIR/miniconda/bin/conda" install -y jupyterlab==4.0
|
||||
"$WORKING_DIR/miniconda/envs/tensorflow2_p39/bin/pip" install matplotlib==3.7.1
|
||||
|
||||
# Create a flag file to indicate setup is complete
|
||||
touch /home/ec2-user/SageMaker/setup-complete
|
||||
|
||||
INNEREOF
|
||||
EOF
|
||||
|
||||
# Make the script executable and run it in the background
|
||||
chmod +x /home/ec2-user/SageMaker/setup-environment.sh
|
||||
sudo -u ec2-user nohup /home/ec2-user/SageMaker/setup-environment.sh > /home/ec2-user/SageMaker/setup.log 2>&1 &
|
||||
|
||||
OnStart:
|
||||
- Content: !Base64 |
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Check if setup is still running or not started
|
||||
if ! [ -f /home/ec2-user/SageMaker/setup-complete ]; then
|
||||
echo "Setup still in progress or not started. Check setup.log for details."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
sudo -u ec2-user -i <<'EOF'
|
||||
unset SUDO_UID
|
||||
|
||||
WORKING_DIR=/home/ec2-user/SageMaker/custom-miniconda
|
||||
source "$WORKING_DIR/miniconda/bin/activate"
|
||||
|
||||
for env in $WORKING_DIR/miniconda/envs/*; do
|
||||
BASENAME=$(basename "$env")
|
||||
source activate "$BASENAME"
|
||||
python -m ipykernel install --user --name "$BASENAME" --display-name "Custom ($BASENAME)"
|
||||
done
|
||||
EOF
|
||||
|
||||
echo "Restarting the Jupyter server.."
|
||||
CURR_VERSION=$(cat /etc/os-release)
|
||||
if [[ $CURR_VERSION == *$"http://aws.amazon.com/amazon-linux-ami/"* ]]; then
|
||||
sudo initctl restart jupyter-server --no-wait
|
||||
else
|
||||
sudo systemctl --no-block restart jupyter-server.service
|
||||
fi
|
||||
|
||||
SageMakerNotebookInstance:
|
||||
Type: AWS::SageMaker::NotebookInstance
|
||||
Properties:
|
||||
InstanceType: ml.g4dn.xlarge
|
||||
NotebookInstanceName: !Ref NotebookName
|
||||
RoleArn: !GetAtt SageMakerExecutionRole.Arn
|
||||
DefaultCodeRepository: !Ref DefaultRepoUrl
|
||||
KmsKeyId: !GetAtt KmsKey.Arn
|
||||
PlatformIdentifier: notebook-al2-v2
|
||||
VolumeSizeInGB: 50
|
||||
LifecycleConfigName: !GetAtt TensorConfigLifecycle.NotebookInstanceLifecycleConfigName
|
||||
|
||||
Outputs:
|
||||
NotebookInstanceName:
|
||||
Description: The name of the created SageMaker Notebook Instance
|
||||
Value: !Ref SageMakerNotebookInstance
|
||||
ExecutionRoleArn:
|
||||
Description: The ARN of the created SageMaker Execution Role
|
||||
Value: !GetAtt SageMakerExecutionRole.Arn
|
||||
KmsKeyArn:
|
||||
Description: The ARN of the created KMS Key for the notebook
|
||||
Value: !GetAtt KmsKey.Arn
|
||||
Loading…
x
Reference in New Issue
Block a user