Gradient Docs
Gradient HomeHelp DeskCommunitySign up free
1.0.0
1.0.0
  • About Paperspace Gradient
  • Get Started
    • Quick Start
    • Core Concepts
    • Install the Gradient CLI
    • Common Errors
  • Tutorials
    • Tutorials List
      • Getting Started with Notebooks
      • Train a Model with the Web UI
      • Train a Model with the CLI
      • Advanced: Distributed training sample project
      • Registering Models in Gradient
      • Using Gradient Deployments
      • Using Custom Containers
  • Notebooks
    • Overview
    • Using Notebooks
      • The Notebook interface
      • Notebook metrics
      • Share a Notebook
      • Fork a Notebook
      • Notebook Directories
      • Notebook Containers
        • Building a Custom Container
      • Notebook Workspace Include Files
      • Community (Public) Notebooks
    • ML Showcase
    • Run on Gradient (GitHub badge)
  • Projects
    • Overview
    • Managing Projects
    • GradientCI
      • GradientCI V1 (Deprecated)
  • Workflows
    • Overview
      • Getting Started with Workflows
      • Workflow Spec
      • Gradient Actions
  • Experiments
    • Overview
    • Using Experiments
      • Containers
      • Single-node & multi-node CLI options
      • Experiment options
      • Gradient Config File
      • Environment variables
      • Experiment datasets
      • Git Commit Tracking
      • Experiment metrics
        • System Metrics
        • Custom Metrics
      • Experiment Logs
      • Experiment Ports
      • GradientCI Experiments
      • Diff Viewer
      • Hyperparameter Tuning
    • Distributed Training
      • Distributed Machine Learning with Tensorflow
      • Distributed Machine Learning with MPI
        • Distributed Training using Horovod
        • Distributed Training Using ChainerMN
  • Jobs
    • Overview
    • Using Jobs
      • Stop a Job
      • Delete a Job
      • List Jobs
      • Job Logs
      • Job Metrics
        • System Metrics
        • Custom Metrics
      • Job Artifacts
      • Public Jobs
      • Building Docker Containers with Jobs
  • Models
    • Overview
    • Managing Models
      • Example: Prepare a TensorFlow Model for Deployments
      • Model Path, Parameters, & Metadata
    • Public Models
  • Deployments
    • Overview
    • Managing Deployments
      • Deployment Containers
        • Custom Deployment Containers
      • Deployment States
      • Deployment Logs
      • Deployment Metrics
      • A Deployed Model's API Endpoint
        • Gradient + TensorFlow Serving
      • Deployment Autoscaling
      • Optimize Models for Inference
  • Data
    • Types of Storage
      • Managing Data in Gradient
        • Managing Persistent Storage with VMs
    • Storage Providers
    • Versioned Datasets
    • Public Datasets Repository
  • TensorBoards
    • Overview
    • Using Tensorboards
      • TensorBoards getting started with Tensorflow
  • Metrics
    • Metrics Overview
    • View and Query Metrics
    • Push Metrics
  • Secrets
    • Overview
    • Using Secrets
  • Gradient SDK
    • Gradient SDK Overview
      • Projects Client
      • Experiments Client
      • Models Client
      • Deployments Client
      • Jobs Client
    • End to end tutorial
    • Full SDK Reference
  • Instances
    • Instance Types
      • Free Instances (Free Tier)
      • Instance Tiers
  • Gradient Cluster
    • Overview
    • Setup
      • Managed Private Clusters
      • Self-Hosted Clusters
        • Pre-installation steps
        • Gradient Installer CLI
        • Terraform
          • Pre-installation steps
          • Install on AWS
          • Install on bare metal / VMs
          • Install on NVIDIA DGX
        • Let's Encrypt DNS Providers
        • Updating your cluster
    • Usage
  • Tags
    • Overview
    • Using Tags
  • Machines (Paperspace CORE)
    • Overview
    • Using Machines
      • Start a Machine
      • Stop a Machine
      • Restart a Machine
      • Update a Machine
      • Destroy a Machine
      • List Machines
      • Show a Machine
      • Wait For a Machine
      • Check a Machine's utilization
      • Check availability
  • Paperspace Account
    • Overview
    • Public Profiles
    • Billing & Subscriptions
    • Hotkeys
    • Teams
      • Creating a Team
      • Upgrading to a Team Plan
  • Release Notes
    • Product release notes
    • CLI/SDK Release notes
Powered by GitBook
On this page
  • Options common to both single-node and multi-node experiments
  • Options specific to single-node experiments
  • Options specific to multi-node experiments
  1. Experiments
  2. Using Experiments

Single-node & multi-node CLI options

Options common to both single-node and multi-node experiments

  --name TEXT                  Name of new experiment  [required]
  --ports TEXT                 Port to use in new experiment
  --workspace TEXT             Path to workspace directory
  --workspaceArchive TEXT      Path to workspace .zip archive
  --workspaceUrl TEXT          Project git repository url
  --workspaceUsername          Github username for private repo
  --workspacePassword          Github password for private repo
  --workingDirectory TEXT      Working directory for the experiment
  --artifactDirectory TEXT     Artifacts directory
  --clusterId TEXT             Cluster ID
  --experimentEnv JSON_STRING  Environment variables in a JSON
  --projectId TEXT             Project ID  [required]
  --modelType TEXT             Model type
  --modelPath TEXT             Model path

workspaceArchive and workspaceUrl are deprecated as of the 0.6.0 release version of the CLI. You can just use workspace going forward!

For workspace, valid schemes for values specifying a remote URL are: https, git+https, and s3, or you can specify "none". This means that, for example, git@github is not a valid scheme for a workspace.

For workspacePassword make sure create an Oauth access token on github

Options specific to single-node experiments

  --container TEXT             Container  [required]
  --machineType TEXT           Machine type  [required]
  --command TEXT               Container entrypoint command  [required]
  --containerUser TEXT         Container user
  --registryUsername TEXT      Registry username
  --registryPassword TEXT      Registry password

A container, machine type, and command are required.

Optionally a Docker registry username and password can be provided for accessing private docker registry container images via the --registryUsername and --registryPassword options.

Also, using the --containerUser option, you can specify a UNIX user name to be used as the UNIX identity for running the specified command in the container. If no containerUser is specified, the user will default to 'root' in the container. This is useful when running a public container image with a different expected user, or when building a container image from a Dockerfile.

Options specific to multi-node experiments

  --experimentTypeId [GRPC|MPI]   Experiment Type ID  [required]
  --workerContainer TEXT          Worker container  [required]
  --workerMachineType TEXT        Worker machine type  [required]
  --workerCommand TEXT            Worker command  [required]
  --workerCount INTEGER           Worker count  [required]
  --parameterServerContainer TEXT
                                  Parameter server container  [required]
  --parameterServerMachineType TEXT
                                  Parameter server machine type  [required]
  --parameterServerCommand TEXT   Parameter server command  [required]
  --parameterServerCount INTEGER  Parameter server count  [required]
  --workerContainerUser TEXT      Worker container user
  --workerRegistryUsername TEXT   Worker container registry username
  --workerRegistryPassword TEXT   Worker registry password
  --parameterServerContainerUser TEXT
                                  Parameter server container user
  --parameterServerRegistryContainerUser TEXT
                                  Parameter server registry container user
  --parameterServerRegistryPassword TEXT
                                  Parameter server registry password

In the case of multi-node experiments, both worker and parameter server instances need a container, machine type, command, count, and optionally a Docker registry username and password.

Note: --containerUser is not a supported option for multi-node experiments currently.

PreviousContainersNextExperiment options

Last updated 5 years ago