- Update API server and worker config schemas - Refine Docker Compose configurations (dev/prod) - Update deployment scripts and documentation
50 lines
902 B
YAML
50 lines
902 B
YAML
worker_id: "docker-worker"
|
|
base_path: "/tmp/fetchml-jobs"
|
|
train_script: "train.py"
|
|
|
|
redis_url: "redis://redis:6379/0"
|
|
|
|
local_mode: true
|
|
|
|
max_workers: 1
|
|
poll_interval_seconds: 2
|
|
|
|
auto_fetch_data: false
|
|
|
|
data_manager_path: "./data_manager"
|
|
dataset_cache_ttl: "30m"
|
|
|
|
data_dir: "/data/active"
|
|
|
|
snapshot_store:
|
|
enabled: true
|
|
endpoint: "blizzard.jfraeys.com"
|
|
secure: true
|
|
bucket: "fetchml-snapshots"
|
|
prefix: "snapshots"
|
|
timeout: "5m"
|
|
max_retries: 3
|
|
|
|
podman_image: "python:3.9-slim"
|
|
container_workspace: "/workspace"
|
|
container_results: "/results"
|
|
gpu_vendor: "nvidia"
|
|
gpu_visible_devices: [0]
|
|
gpu_devices: ["/dev/nvidia0"]
|
|
|
|
|
|
resources:
|
|
max_workers: 1
|
|
desired_rps_per_worker: 2
|
|
podman_cpus: "2"
|
|
podman_memory: "4Gi"
|
|
|
|
metrics:
|
|
enabled: true
|
|
listen_addr: ":9100"
|
|
metrics_flush_interval: "500ms"
|
|
|
|
task_lease_duration: "30m"
|
|
heartbeat_interval: "1m"
|
|
max_retries: 3
|
|
graceful_timeout: "5m"
|