clearml-agent/docs/clearml.conf

# CLEARML-AGENT configuration file
api {
    api_server: https://demoapi.demo.clear.ml
    web_server: https://demoapp.demo.clear.ml
    files_server: https://demofiles.demo.clear.ml

    # Credentials are generated in the webapp, https://app.clear.ml/settings/workspace-configuration
    # Overridden with os environment: CLEARML_API_ACCESS_KEY / CLEARML_API_SECRET_KEY
    credentials {"access_key": "EGRTCO8JMSIGI6S39GTP43NFWXDQOW", "secret_key": "x!XTov_G-#vspE*Y(h$Anm&DIc5Ou-F)jsl$PdOyj5wG1&E!Z8"}

    # verify host ssl certificate, set to False only if you have a very good reason
    verify_certificate: True
}

agent {
    # Set GIT user/pass credentials (if user/pass are set, GIT protocol will be set to https)
    # leave blank for GIT SSH credentials (set force_git_ssh_protocol=true to force SSH protocol)
    # **Notice**: GitHub personal token is equivalent to password, you can put it directly into `git_pass`
    # To learn how to generate git token GitHub/Bitbucket/GitLab:
    # https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token
    # https://support.atlassian.com/bitbucket-cloud/docs/app-passwords/
    # https://docs.gitlab.com/ee/user/profile/personal_access_tokens.html
    git_user=""
    git_pass=""
    # Limit credentials to a single domain, for example: github.com,
    # all other domains will use public access (no user/pass). Default: always send user/pass for any VCS domain
    git_host=""

    # Force GIT protocol to use SSH regardless of the git url (Assumes GIT user/pass are blank)
    force_git_ssh_protocol: false
    # Force a specific SSH port when converting http to ssh links (the domain is kept the same)
    # force_git_ssh_port: 0
    # Force a specific SSH username when converting http to ssh links (the default username is 'git')
    # force_git_ssh_user: git

    # unique name of this worker, if None, created based on hostname:process_id
    # Overridden with os environment: CLEARML_WORKER_ID
    # worker_id: "clearml-agent-machine1:gpu0"
    worker_id: ""

    # worker name, replaces the hostname when creating a unique name for this worker
    # Overridden with os environment: CLEARML_WORKER_NAME
    # worker_name: "clearml-agent-machine1"
    worker_name: ""

    # Set the python version to use when creating the virtual environment and launching the experiment
    # Example values: "/usr/bin/python3" or "/usr/local/bin/python3.6"
    # The default is the python executing the clearml_agent
    python_binary: ""
    # ignore any requested python version (Default: False, if a Task was using a
    # specific python version and the system supports multiple python the agent will use the requested python version)
    # ignore_requested_python_version: true

    # select python package manager:
    # currently supported: pip, conda and poetry
    # if "pip" or "conda" are used, the agent installs the required packages
    # based on the "installed packages" section of the Task. If the "installed packages" is empty,
    # it will revert to using `requirements.txt` from the repository's root directory.
    # If Poetry is selected and the root repository contains `poetry.lock` or `pyproject.toml`,
    # the "installed packages" section is ignored, and poetry is used.
    # If Poetry is selected and no lock file is found, it reverts to "pip" package manager behaviour.
    package_manager: {
        # supported options: pip, conda, poetry
        type: pip,

        # specify pip version to use (examples "<20", "==19.3.1", "", empty string will install the latest version)
        # pip_version: "<20"
        # specify poetry version to use (examples "<2", "==1.1.1", "", empty string will install the latest version)
        # poetry_version: "<2",

        # virtual environment inheres packages from system
        system_site_packages: false,
        # install with --upgrade
        force_upgrade: false,

        # additional artifact repositories to use when installing python packages
        # extra_index_url: ["https://allegroai.jfrog.io/clearml/api/pypi/public/simple"]
        extra_index_url: []

        # additional conda channels to use when installing with conda package manager
        conda_channels: ["pytorch", "conda-forge", "defaults", ]
        # conda_full_env_update: false
        # conda_env_as_base_docker: false

        # set the priority packages to be installed before the rest of the required packages
        # priority_packages: ["cython", "numpy", "setuptools", ]

        # set the optional priority packages to be installed before the rest of the required packages,
        # In case a package installation fails, the package will be ignored,
        # and the virtual environment process will continue
        # priority_optional_packages: ["pygobject", ]

        # set the post packages to be installed after all the rest of the required packages
        # post_packages: ["horovod", ]

        # set the optional post packages to be installed after all the rest of the required packages,
        # In case a package installation fails, the package will be ignored,
        # and the virtual environment process will continue
        # post_optional_packages: []

        # set to True to support torch nightly build installation,
        # notice: torch nightly builds are ephemeral and are deleted from time to time
        torch_nightly: false,
    },

    # target folder for virtual environments builds, created when executing experiment
    venvs_dir = ~/.clearml/venvs-builds

    # cached virtual environment folder
    venvs_cache: {
        # maximum number of cached venvs
        max_entries: 10
        # minimum required free space to allow for cache entry, disable by passing 0 or negative value
        free_space_threshold_gb: 2.0
        # unmark to enable virtual environment caching
        # path: ~/.clearml/venvs-cache
    },

    # cached git clone folder
    vcs_cache: {
        enabled: true,
        path: ~/.clearml/vcs-cache
    },

    # DEPRECATED: please use `venvs_cache` and set `venvs_cache.path`
    # use venv-update in order to accelerate python virtual environment building
    # Still in beta, turned off by default
    # venv_update: {
    #     enabled: false,
    # },

    # cached folder for specific python package download (mostly pytorch versions)
    pip_download_cache {
        enabled: true,
        path: ~/.clearml/pip-download-cache
    },

    translate_ssh: true,
    # reload configuration file every daemon execution
    reload_config: false,

    # pip cache folder mapped into docker, used for python package caching
    docker_pip_cache = ~/.clearml/pip-cache
    # apt cache folder mapped into docker, used for ubuntu package caching
    docker_apt_cache = ~/.clearml/apt-cache

    # optional arguments to pass to docker image
    # these are local for this agent and will not be updated in the experiment's docker_cmd section
    # extra_docker_arguments: ["--ipc=host", "-v", "/mnt/host/data:/mnt/data"]

    # optional shell script to run in docker when started before the experiment is started
    # extra_docker_shell_script: ["apt-get install -y bindfs", ]

    # Install the required packages for opencv libraries (libsm6 libxext6 libxrender-dev libglib2.0-0),
    # for backwards compatibility reasons, true as default,
    # change to false to skip installation and decrease docker spin up time
    # docker_install_opencv_libs: true

    # set to true in order to force "docker pull" before running an experiment using a docker image.
    # This makes sure the docker image is updated.
    docker_force_pull: false

    default_docker: {
        # default docker image to use when running in docker mode
        image: "nvidia/cuda:10.2-cudnn7-runtime-ubuntu18.04"

        # optional arguments to pass to docker image
        # arguments: ["--ipc=host"]

        # lookup table rules for default container
        # first matched rule will be picked, according to rule order
        # enterprise version only
        # match_rules: [
        #     {
        #         image: "nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04"
        #         arguments: "-e define=value"
        #         match: {
        #             script{
        #                 # Optional: must match all requirements (not partial)
        #                 requirements: {
        #                     # version selection matching PEP-440
        #                     pip: {
        #                         tensorflow: "~=2.6"
        #                     },
        #                 }
        #                 # Optional: matching based on regular expression, example: "^exact_match$"
        #                 repository: "/my_repository/"
        #                 branch: "main"
        #                 binary: "python3.6"
        #             }
        #             # Optional: matching based on regular expression, example: "^exact_match$"
        #             project: "project/sub_project"
        #         }
        #     },
        #     {
        #         image: "nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04"
        #         arguments: "-e define=value"
        #         match: {
        #             # must match all requirements (not partial)
        #             script{
        #                 requirements: {
        #                     conda: {
        #                         torch: ">=2.6,<2.8"
        #                     }
        #                 }
        #                 # no repository matching required
        #                 repository: ""
        #             }
        #             # no container image matching required (allow to replace one requested container with another)
        #             container: ""
        #             # no repository matching required
        #             project: ""
        #         }
        #     },
        # ]
    }

    # set the OS environments based on the Task's Environment section before launching the Task process.
    enable_task_env: false

    # CUDA versions used for Conda setup & solving PyTorch wheel packages
    # it Should be detected automatically. Override with os environment CUDA_VERSION / CUDNN_VERSION
    # cuda_version: 10.1
    # cudnn_version: 7.6

    # Hide docker environment variables containing secrets when printing out the docker command by replacing their
    # values with "********". Turning this feature on will hide the following environment variables values:
    #   CLEARML_API_SECRET_KEY, CLEARML_AGENT_GIT_PASS, AWS_SECRET_ACCESS_KEY, AZURE_STORAGE_KEY
    # To include more environment variables, add their keys to the "extra_keys" list. E.g. to make sure the value of
    # your custom environment variable named MY_SPECIAL_PASSWORD will not show in the logs when included in the
    # docker command, set:
    #   extra_keys: ["MY_SPECIAL_PASSWORD"]
    hide_docker_command_env_vars {
        enabled: true
        extra_keys: []
        parse_embedded_urls: true
    }

    # allow to set internal mount points inside the docker,
    # especially useful for non-root docker container images.
    # docker_internal_mounts {
    #     sdk_cache: "/clearml_agent_cache"
    #     apt_cache: "/var/cache/apt/archives"
    #     ssh_folder: "/root/.ssh"
    #     pip_cache: "/root/.cache/pip"
    #     poetry_cache: "/root/.cache/pypoetry"
    #     vcs_cache: "/root/.clearml/vcs-cache"
    #     venv_build: "~/.clearml/venvs-builds"
    #     pip_download: "/root/.clearml/pip-download-cache"
    # }

    # Name docker containers created by the daemon using the following string format (supported from Docker 0.6.5)
    # Allowed variables are task_id, worker_id and rand_string (random lower-case letters string, up to 32 characters)
    # Note: resulting name must start with an alphanumeric character and
    #       continue with alphanumeric characters, underscores (_), dots (.) and/or dashes (-)
    # docker_container_name_format: "clearml-id-{task_id}-{rand_string:.8}"
}

sdk {
    # CLEARML - default SDK configuration

    storage {
        cache {
            # Defaults to system temp folder / cache
            default_base_dir: "~/.clearml/cache"
        }

        direct_access: [
            # Objects matching are considered to be available for direct access, i.e. they will not be downloaded
            # or cached, and any download request will return a direct reference.
            # Objects are specified in glob format, available for url and content_type.
            { url: "file://*" }  # file-urls are always directly referenced
        ]
    }

    metrics {
        # History size for debug files per metric/variant. For each metric/variant combination with an attached file
        # (e.g. debug image event), file names for the uploaded files will be recycled in such a way that no more than
        # X files are stored in the upload destination for each metric/variant combination.
        file_history_size: 100

        # Max history size for matplotlib imshow files per plot title.
        # File names for the uploaded images will be recycled in such a way that no more than
        # X images are stored in the upload destination for each matplotlib plot title.
        matplotlib_untitled_history_size: 100

        # Limit the number of digits after the dot in plot reporting (reducing plot report size)
        # plot_max_num_digits: 5

        # Settings for generated debug images
        images {
            format: JPEG
            quality: 87
            subsampling: 0
        }

        # Support plot-per-graph fully matching Tensorboard behavior (i.e. if this is set to True, each series should have its own graph)
        tensorboard_single_series_per_graph: False
    }

    network {
        metrics {
            # Number of threads allocated to uploading files (typically debug images) when transmitting metrics for
            # a specific iteration
            file_upload_threads: 4

            # Warn about upload starvation if no uploads were made in specified period while file-bearing events keep
            # being sent for upload
            file_upload_starvation_warning_sec: 120
        }

        iteration {
            # Max number of retries when getting frames if the server returned an error (http code 500)
            max_retries_on_server_error: 5
            # Backoff factory for consecutive retry attempts.
            # SDK will wait for {backoff factor} * (2 ^ ({number of total retries} - 1)) between retries.
            retry_backoff_factor_sec: 10
        }
    }
    aws {
        s3 {
            # S3 credentials, used for read/write access by various SDK elements

            # default, used for any bucket not specified below
            key: ""
            secret: ""
            region: ""
            # Or enable credentials chain to let Boto3 pick the right credentials.
            # This includes picking credentials from environment variables,
            # credential file and IAM role using metadata service.
            # Refer to the latest Boto3 docs
            use_credentials_chain: false

            credentials: [
                # specifies key/secret credentials to use when handling s3 urls (read or write)
                # {
                #     bucket: "my-bucket-name"
                #     key: "my-access-key"
                #     secret: "my-secret-key"
                # },
                # {
                #     # This will apply to all buckets in this host (unless key/value is specifically provided for a given bucket)
                #     host: "my-minio-host:9000"
                #     key: "12345678"
                #     secret: "12345678"
                #     multipart: false
                #     secure: false
                #     verify: /path/to/ca/bundle.crt OR false to not verify
                # }
            ]
        }
        boto3 {
            pool_connections: 512
            max_multipart_concurrency: 16
        }
    }
    google.storage {
        # # Default project and credentials file
        # # Will be used when no bucket configuration is found
        # project: "clearml"
        # credentials_json: "/path/to/credentials.json"

        # # Specific credentials per bucket and sub directory
        # credentials = [
        #     {
        #         bucket: "my-bucket"
        #         subdir: "path/in/bucket" # Not required
        #         project: "clearml"
        #         credentials_json: "/path/to/credentials.json"
        #     },
        # ]
    }
    azure.storage {
        # containers: [
        #     {
        #         account_name: "clearml"
        #         account_key: "secret"
        #         # container_name:
        #     }
        # ]
    }

    log {
        # debugging feature: set this to true to make null log propagate messages to root logger (so they appear in stdout)
        null_log_propagate: False
        task_log_buffer_capacity: 66

        # disable urllib info and lower levels
        disable_urllib3_info: True
    }

    development {
        # Development-mode options

        # dev task reuse window
        task_reuse_time_window_in_hours: 72.0

        # Run VCS repository detection asynchronously
        vcs_repo_detect_async: True

        # Store uncommitted git/hg source code diff in experiment manifest when training in development mode
        # This stores "git diff" or "hg diff" into the experiment's "script.requirements.diff" section
        store_uncommitted_code_diff_on_train: True

        # Support stopping an experiment in case it was externally stopped, status was changed or task was reset
        support_stopping: True

        # Default Task output_uri. if output_uri is not provided to Task.init, default_output_uri will be used instead.
        default_output_uri: ""

        # Development mode worker
        worker {
            # Status report period in seconds
            report_period_sec: 2

            # ping to the server - check connectivity
            ping_period_sec: 30

            # Log all stdout & stderr
            log_stdout: True
        }
    }

    # Apply top-level environment section from configuration into os.environ
    apply_environment: true
    # Top-level environment section is in the form of:
    #   environment {
    #     key: value
    #     ...
    #   }
    # and is applied to the OS environment as `key=value` for each key/value pair

    # Apply top-level files section from configuration into local file system
    apply_files: true
    # Top-level files section allows auto-generating files at designated paths with a predefined contents
    # and target format. Options include:
    #  contents: the target file's content, typically a string (or any base type int/float/list/dict etc.)
    #  format: a custom format for the contents. Currently supported value is `base64` to automatically decode a
    #          base64-encoded contents string, otherwise ignored
    #  path: the target file's path, may include ~ and inplace env vars
    #  target_format: format used to encode contents before writing into the target file. Supported values are json,
    #                 yaml, yml and bytes (in which case the file will be written in binary mode). Default is text mode.
    #  overwrite: overwrite the target file in case it exists. Default is true.
    #
    # Example:
    #   files {
    #     myfile1 {
    #       contents: "The quick brown fox jumped over the lazy dog"
    #       path: "/tmp/fox.txt"
    #     }
    #     myjsonfile {
    #       contents: {
    #         some {
    #           nested {
    #             value: [1, 2, 3, 4]
    #           }
    #         }
    #       }
    #       path: "/tmp/test.json"
    #       target_format: json
    #     }
    #   }
}