mlops-v2/config-aml.yml

76 строки
2.3 KiB
YAML

variables:
ap_vm_image: ubuntu-20.04
# Training pipeline settings
# Training dataset settings
training_dataset_name: uci-credit
training_dataset_description: uci_credit
training_dataset_local_path: data/training/
training_dataset_path_on_datastore: data/training/
training_dataset_type: local
training_dataset_storage_url: 'https://azureaidemostorage.blob.core.windows.net/data/'
# Training AzureML Environment name
training_env_name: credit-training
# Training AzureML Environment conda yaml
training_env_conda_yaml: mlops/environments/train.yml
# Name for the training pipeline
training_pipeline_name: credit-training
# Compute target for pipeline
training_target: cpu-cluster
training_target_sku: STANDARD_D2_V2
training_target_min_nodes: 0
training_target_max_nodes: 4
# Training arguments specification; use azureml:dataset_name:version to reference an AML Dataset for --data_path
training_arguments: --data_path azureml:uci-credit:1
# Name under which the model will be registered
model_name: credit-ci
# Batch pipeline settings
# Batch scoring dataset settings
scoring_dataset_name: credit-batch-input
scoring_dataset_description: credit-batch-input
scoring_dataset_local_path: data/scoring/
scoring_dataset_path_on_datastore: data/scoring/
scoring_dataset_type: local
scoring_dataset_storage_url: 'https://azureaidemostorage.blob.core.windows.net/data/'
# Batch AzureML Environment name
batch_env_name: credit-batch
# Batch AzureML Environment conda yaml
batch_env_conda_yaml: mlops/environments/batch.yml
# Name for the batch scoring pipeline
batch_pipeline_name: credit-batch-scoring
# Compute target for pipeline
batch_target: cpu-cluster
#not needed because batch uses the same target as training
# batch_target_sku: STANDARD_D2_V2
# batch_target_min_nodes: 0
# batch_target_max_nodes: 4
# Input batch dataset
batch_input_dataset_name: credit-batch-input
# Output dataset with results
batch_output_dataset_name: credit-batch-output
batch_output_path_on_datastore: credit-batch-scoring-results/{run-id}
batch_output_filename: results.csv
# Parallelization settings
batch_mini_batch_size: 8
batch_error_threshold: 1
batch_process_count_per_node: 1
batch_node_count: 1