torc 0.23.0

Workflow management system
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83

# Zip Parameter Mode Example
# Demonstrates using parameter_mode: zip for paired parameter expansion
#
# When using Cartesian product (default): 3 datasets × 3 models = 9 jobs
# When using zip mode: 3 pairs = 3 jobs (dataset[i] paired with model[i])
#
# This is useful when you have pre-determined parameter combinations rather than
# wanting to test all possible combinations.

name: zip_parameter_example
description: Example workflow demonstrating zip parameter mode for paired parameters

jobs:
  # Setup job - runs once before all training jobs
  - name: setup_environment
    command: |
      echo "Setting up training environment"
      mkdir -p /models /results

  # Training jobs using zip mode - each dataset is paired with a specific model
  # Instead of 3×3=9 combinations, we get exactly 3 jobs:
  #   - cifar10 with resnet
  #   - mnist with cnn
  #   - imagenet with transformer
  - name: train_{dataset}_{model}
    command: |
      python train.py \
        --dataset={dataset} \
        --model={model} \
        --output=/models/{dataset}_{model}.pt
    depends_on:
      - setup_environment
    output_files:
      - model_{dataset}_{model}
    parameters:
      dataset: "['cifar10', 'mnist', 'imagenet']"
      model: "['resnet', 'cnn', 'transformer']"
    parameter_mode: zip

  # Evaluation job that processes all models
  # Note: This job uses the same parameters with zip mode to wait for the
  # correct corresponding training jobs
  - name: evaluate_{dataset}_{model}
    command: |
      python evaluate.py \
        --model=/models/{dataset}_{model}.pt \
        --output=/results/{dataset}_{model}_metrics.json
    depends_on:
      - train_{dataset}_{model}
    input_files:
      - model_{dataset}_{model}
    output_files:
      - metrics_{dataset}_{model}
    parameters:
      dataset: "['cifar10', 'mnist', 'imagenet']"
      model: "['resnet', 'cnn', 'transformer']"
    parameter_mode: zip

  # Final aggregation job
  - name: aggregate_results
    command: |
      python aggregate.py \
        --input-dir=/results \
        --output=/results/summary.json
    # Use regex to depend on all evaluation jobs
    depends_on_regexes:
      - "evaluate_.*"

# File specifications also support zip mode
files:
  - name: model_{dataset}_{model}
    path: /models/{dataset}_{model}.pt
    parameters:
      dataset: "['cifar10', 'mnist', 'imagenet']"
      model: "['resnet', 'cnn', 'transformer']"
    parameter_mode: zip

  - name: metrics_{dataset}_{model}
    path: /results/{dataset}_{model}_metrics.json
    parameters:
      dataset: "['cifar10', 'mnist', 'imagenet']"
      model: "['resnet', 'cnn', 'transformer']"
    parameter_mode: zip