# ClearML SDK configuration file api { # web_server on port 8080 web_server: "http://localhost:8080" # Notice: 'api_server' is the api server (default port 8008), not the web server. api_server: "http://localhost:8008" # file server on port 8081 files_server: "http://localhost:8081" # Credentials are generated using the webapp, http://localhost:8080/profile 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 } sdk { # ClearML - default SDK configuration storage { path_substitution = [ # Replace registered links with local prefixes, # Solve mapping issues, and allow for external resource caching. # { # registered_prefix = "s3://bucket/research" # local_prefix = "file:///mnt/shared/bucket/research" # }, # { # registered_prefix = "file:///mnt/shared/folder/" # local_prefix = "file:///home/user/shared/folder" # } ] cache { # Defaults to /clearml_cache default_base_dir: "~/.clearml/cache" default_cache_manager_size: 100 } } 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 factor 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 region: "" # Specify explicit keys key: "" secret: "" # Specify profile profile: "" # 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 # Additional ExtraArgs passed to boto3 when uploading files. Can also be set per-bucket under "credentials". extra_args: {} credentials: [ # specifies key/secret credentials to use when handling s3 urls (read or write) # Note that all all fields in the global s3 config section are supported here # { # 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 # } ] } boto3 { pool_connections: 512 max_multipart_concurrency: 16 multipart_threshold: 8388608 # 8MB multipart_chunksize: 8388608 # 8MB } } 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 { # # Optional (default, unset) # # max_connections: 2 # 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 into the experiment's "script.requirements.diff" section store_uncommitted_code_diff: true store_code_diff_from_remote: false # 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: "" # Default auto generated requirements optimize for smaller requirements # If True, analyze the entire repository regardless of the entry point. # If False, first analyze the entry point script, if it does not contain other to local files, # do not analyze the entire repository. force_analyze_entire_repo: false # If set to true, *clearml* update message will not be printed to the console # this value can be overwritten with os environment variable CLEARML_SUPPRESS_UPDATE_MESSAGE=1 suppress_update_message: false # If this flag is true (default is false), instead of analyzing the code with Pigar, analyze with `pip freeze` detect_with_pip_freeze: false detect_with_conda_freeze: false # If True, provide a detailed report of all python package imports # as comments inside the "Installed packages" section detailed_import_report: false # Log specific environment variables. OS environments are listed in the "Environment" section # of the Hyper-Parameters. # multiple selected variables are supported including the suffix '*'. # For example: "AWS_*" will log any OS environment variable starting with 'AWS_'. # This value can be overwritten with os environment variable CLEARML_LOG_ENVIRONMENT="[AWS_*, CUDA_VERSION]" # Example: log_os_environments: ["AWS_*", "CUDA_VERSION"] log_os_environments: [] # Development mode worker worker { # Status report period in seconds report_period_sec: 2 # The number of events to report report_event_flush_threshold: 100 # ping to the server - check connectivity ping_period_sec: 30 # Log all stdout & stderr log_stdout: true # compatibility feature, report memory usage for the entire machine # default (false), report only on the running process and its sub-processes report_global_mem_used: false # if provided, start resource reporting after this amount of seconds # report_start_sec: 30 # set the initial time (seconds) to wait for iteration reporting to be used as x-axis for the # resource monitoring, if timeout exceeds then reverts to "seconds from start" # wait_for_first_iteration_to_start_sec: 30 # set the maximum time (seconds) to allow the resource monitoring to revert back to # iteration reporting x-axis after starting to report "seconds from start" # max_wait_for_first_iteration_to_start_sec: 1800 } artifacts { # set default extension_name for pandas DataFrame objects # valid values are: ``.csv.gz``, ``.parquet``, ``.feather``, ``.pickle`` # extension_name supplied to Task.upload_artifact is prioritized over this value default_pandas_dataframe_extension_name: "" } } }