clearml/docs/trains.conf

134 lines
4.5 KiB
Plaintext
Raw Normal View History

2019-06-10 17:00:28 +00:00
# TRAINS SDK configuration file
api {
2019-06-11 11:36:36 +00:00
# Notice: 'host' is the api server (default port 8008), not the web server.
host: http://localhost:8008
# Credentials are generated in the webapp, http://localhost:8080/admin
credentials {"access_key": "EGRTCO8JMSIGI6S39GTP43NFWXDQOW", "secret_key": "x!XTov_G-#vspE*Y(h$Anm&DIc5Ou-F)jsl$PdOyj5wG1&E!Z8"}
2019-06-10 17:00:28 +00:00
}
sdk {
# TRAINS - default SDK configuration
storage {
cache {
# Defaults to system temp folder / cache
default_base_dir: "~/.trains/cache"
}
}
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
# Settings for generated debug images
images {
format: JPEG
quality: 87
subsampling: 0
}
}
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: ""
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
# }
]
}
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: "trains"
# credentials_json: "/path/to/credentials.json"
# # Specific credentials per bucket and sub directory
# credentials = [
# {
# bucket: "my-bucket"
# subdir: "path/in/bucket" # Not required
# project: "trains"
# credentials_json: "/path/to/credentials.json"
# },
# ]
}
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: False
# 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
# Development mode worker
worker {
# Status report period in seconds
report_period_sec: 2
# Log all stdout & stderr
log_stdout: True
}
}
}