mirror of
https://github.com/ghndrx/kubeflow-pipelines.git
synced 2026-02-09 22:35:04 +00:00
Greg Hendrickson
5f554ea769
- Add config.py with dataclass-based configuration from env vars - Remove hardcoded RunPod endpoint and credentials - Consolidate duplicate training components into single reusable function - Add .env.example with all configurable options - Update README with environment variable documentation - Add Kubernetes secrets example for production deployments - Add timeout and error handling improvements BREAKING: Pipeline parameters now use env vars by default. Set RUNPOD_API_KEY, RUNPOD_ENDPOINT, S3_BUCKET, and AWS creds.
38 lines
1.6 KiB
Plaintext
38 lines
1.6 KiB
Plaintext
# =============================================================================
|
|
# Healthcare ML Pipeline Configuration
|
|
# =============================================================================
|
|
# Copy this file to .env and fill in your values.
|
|
# DO NOT commit .env to version control!
|
|
|
|
# -----------------------------------------------------------------------------
|
|
# RunPod Configuration (Required)
|
|
# -----------------------------------------------------------------------------
|
|
RUNPOD_API_KEY=your_runpod_api_key_here
|
|
RUNPOD_ENDPOINT=your_endpoint_id_here
|
|
RUNPOD_API_BASE=https://api.runpod.ai/v2
|
|
|
|
# -----------------------------------------------------------------------------
|
|
# AWS Configuration (Required for model storage)
|
|
# -----------------------------------------------------------------------------
|
|
AWS_ACCESS_KEY_ID=
|
|
AWS_SECRET_ACCESS_KEY=
|
|
AWS_SESSION_TOKEN= # Optional - for assumed role sessions
|
|
AWS_REGION=us-east-1
|
|
S3_BUCKET=your-model-bucket
|
|
|
|
# -----------------------------------------------------------------------------
|
|
# Model Training Defaults (Optional - sensible defaults provided)
|
|
# -----------------------------------------------------------------------------
|
|
BASE_MODEL=emilyalsentzer/Bio_ClinicalBERT
|
|
MAX_SAMPLES=10000
|
|
EPOCHS=3
|
|
BATCH_SIZE=16
|
|
EVAL_SPLIT=0.1
|
|
LEARNING_RATE=2e-5
|
|
|
|
# -----------------------------------------------------------------------------
|
|
# Pipeline Runtime Settings (Optional)
|
|
# -----------------------------------------------------------------------------
|
|
POLL_INTERVAL_SECONDS=10 # How often to check training status
|
|
TRAINING_TIMEOUT_SECONDS=3600 # Max training time (1 hour default)
|