mirror of
https://github.com/hanzo-ml/katib.git
synced 2026-10-30 14:46:14 +00:00
Mahdi KhashanandGitHub
19db2d47d4
* move to ghcr Signed-off-by: mahdikhashan <[email protected]> * move images to ghcr Signed-off-by: mahdikhashan <[email protected]> * manifests Signed-off-by: mahdikhashan <[email protected]> * change registry in all path Signed-off-by: mahdikhashan <[email protected]> * update script Signed-off-by: mahdikhashan <[email protected]> * fix Signed-off-by: mahdikhashan <[email protected]> * fix Signed-off-by: mahdikhashan <[email protected]> * slight fix Signed-off-by: mahdikhashan <[email protected]> --------- Signed-off-by: mahdikhashan <[email protected]> Signed-off-by: Mahdi Khashan <[email protected]>
72 lines
2.0 KiB
YAML
72 lines
2.0 KiB
YAML
---
|
|
apiVersion: kubeflow.org/v1beta1
|
|
kind: Experiment
|
|
metadata:
|
|
namespace: kubeflow
|
|
name: pytorchjob-mnist
|
|
spec:
|
|
parallelTrialCount: 3
|
|
maxTrialCount: 12
|
|
maxFailedTrialCount: 3
|
|
objective:
|
|
type: minimize
|
|
goal: 0.001
|
|
objectiveMetricName: loss
|
|
algorithm:
|
|
algorithmName: random
|
|
parameters:
|
|
- name: lr
|
|
parameterType: double
|
|
feasibleSpace:
|
|
min: "0.01"
|
|
max: "0.05"
|
|
- name: momentum
|
|
parameterType: double
|
|
feasibleSpace:
|
|
min: "0.5"
|
|
max: "0.9"
|
|
trialTemplate:
|
|
primaryContainerName: pytorch
|
|
trialParameters:
|
|
- name: learningRate
|
|
description: Learning rate for the training model
|
|
reference: lr
|
|
- name: momentum
|
|
description: Momentum for the training model
|
|
reference: momentum
|
|
trialSpec:
|
|
apiVersion: kubeflow.org/v1
|
|
kind: PyTorchJob
|
|
spec:
|
|
pytorchReplicaSpecs:
|
|
Master:
|
|
replicas: 1
|
|
restartPolicy: OnFailure
|
|
template:
|
|
spec:
|
|
containers:
|
|
- name: pytorch
|
|
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:latest
|
|
command:
|
|
- "python3"
|
|
- "/opt/pytorch-mnist/mnist.py"
|
|
- "--epochs=1"
|
|
- "--batch-size=16"
|
|
- "--lr=${trialParameters.learningRate}"
|
|
- "--momentum=${trialParameters.momentum}"
|
|
Worker:
|
|
replicas: 1
|
|
restartPolicy: OnFailure
|
|
template:
|
|
spec:
|
|
containers:
|
|
- name: pytorch
|
|
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:latest
|
|
command:
|
|
- "python3"
|
|
- "/opt/pytorch-mnist/mnist.py"
|
|
- "--epochs=1"
|
|
- "--batch-size=16"
|
|
- "--lr=${trialParameters.learningRate}"
|
|
- "--momentum=${trialParameters.momentum}"
|