-
Notifications
You must be signed in to change notification settings - Fork 65
183 lines (181 loc) · 15.1 KB
/
regression_tests.yml
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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
name: Containerized Regression Tests
on:
pull_request:
branches:
- 'main'
jobs:
build_and_push_jax_docker_image:
runs-on: self-hosted
steps:
- uses: actions/checkout@v2
- name: Build and push docker images
run: |
GIT_BRANCH=${{ github.head_ref || github.ref_name }}
FRAMEWORK=jax
IMAGE_NAME="algoperf_${FRAMEWORK}_${GIT_BRANCH}"
cd $HOME/algorithmic-efficiency/docker
docker build --no-cache -t $IMAGE_NAME . --build-arg framework=$FRAMEWORK --build-arg branch=$GIT_BRANCH
BUILD_RETURN=$?
if [[ ${BUILD_RETURN} != 0 ]]; then exit ${BUILD_RETURN}; fi
docker tag $IMAGE_NAME us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/$IMAGE_NAME
docker push us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/$IMAGE_NAME
build_and_push_pytorch_docker_image:
runs-on: self-hosted
steps:
- uses: actions/checkout@v2
- name: Build and push docker images
run: |
GIT_BRANCH=${{ github.head_ref || github.ref_name }}
FRAMEWORK=pytorch
IMAGE_NAME="algoperf_${FRAMEWORK}_${GIT_BRANCH}"
cd $HOME/algorithmic-efficiency/docker
docker build --no-cache -t $IMAGE_NAME . --build-arg framework=$FRAMEWORK --build-arg branch=$GIT_BRANCH
BUILD_RETURN=$?
if [[ ${BUILD_RETURN} != 0 ]]; then exit ${BUILD_RETURN}; fi
docker tag $IMAGE_NAME us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/$IMAGE_NAME
docker push us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/$IMAGE_NAME
fastmri_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d fastmri -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w fastmri -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
imagenet_resnet_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d imagenet -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w imagenet_resnet -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
imagenet_vit_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d imagenet -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w imagenet_vit -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
ogbg_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d ogbg -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w ogbg -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
criteo_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d criteo1tb -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w criteo1tb -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
librispeech_conformer_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d librispeech -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w librispeech_conformer -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
librispeech_deepspeech_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d librispeech -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w librispeech_deepspeech -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
wmt_jax:
runs-on: self-hosted
needs: build_and_push_jax_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_jax_${{ github.head_ref || github.ref_name }} -d wmt -f jax -s reference_algorithms/paper_baselines/adamw/jax/submission.py -w wmt -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
fastmri_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d fastmri -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w fastmri -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
imagenet_resnet_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d imagenet -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w imagenet_resnet -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
imagenet_vit_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d imagenet -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w imagenet_vit -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
ogbg_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d ogbg -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w ogbg -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
criteo_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d criteo1tb -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w criteo1tb -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
exit $?
librispeech_conformer_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d librispeech -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w librispeech_conformer -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
librispeech_deepspeech_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d librispeech -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w librispeech_deepspeech -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false
wmt_pytorch:
runs-on: self-hosted
needs: build_and_push_pytorch_docker_image
steps:
- uses: actions/checkout@v2
- name: Run containerized workload
run: |
docker pull us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }}
docker run -v $HOME/data/:/data/ -v $HOME/experiment_runs/:/experiment_runs -v $HOME/experiment_runs/logs:/logs --gpus all --ipc=host us-central1-docker.pkg.dev/training-algorithms-external/mlcommons-docker-repo/algoperf_pytorch_${{ github.head_ref || github.ref_name }} -d wmt -f pytorch -s reference_algorithms/paper_baselines/adamw/pytorch/submission.py -w wmt -t reference_algorithms/paper_baselines/adamw/tuning_search_space.json -e tests/regression_tests/adamw -m 10 -c False -o True -r false