mirror of
https://github.com/hanzo-ml/katib.git
synced 2026-09-24 00:31:27 +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]>
75 lines
1.9 KiB
YAML
75 lines
1.9 KiB
YAML
---
|
|
apiVersion: kubeflow.org/v1beta1
|
|
kind: Experiment
|
|
metadata:
|
|
namespace: kubeflow
|
|
name: optuna-distribution
|
|
spec:
|
|
objective:
|
|
type: minimize
|
|
goal: 0.05
|
|
objectiveMetricName: loss
|
|
algorithm:
|
|
algorithmName: tpe
|
|
parallelTrialCount: 3
|
|
maxTrialCount: 12
|
|
maxFailedTrialCount: 3
|
|
parameters:
|
|
- name: lr
|
|
parameterType: double
|
|
feasibleSpace:
|
|
min: "1"
|
|
max: "5"
|
|
step: "0.1"
|
|
distribution: uniform
|
|
- name: momentum
|
|
parameterType: double
|
|
feasibleSpace:
|
|
min: "0.001"
|
|
max: "3"
|
|
distribution: logUniform
|
|
- name: epochs
|
|
parameterType: int
|
|
feasibleSpace:
|
|
min: "1"
|
|
max: "3"
|
|
distribution: uniform
|
|
- name: batch_size
|
|
parameterType: int
|
|
feasibleSpace:
|
|
min: "32"
|
|
max: "64"
|
|
distribution: logUniform
|
|
trialTemplate:
|
|
primaryContainerName: training-container
|
|
trialParameters:
|
|
- name: learningRate
|
|
description: Learning rate for the training model
|
|
reference: lr
|
|
- name: momentum
|
|
description: Momentum for the training model
|
|
reference: momentum
|
|
- name: epochs
|
|
description: Epochs
|
|
reference: epochs
|
|
- name: batchSize
|
|
description: Batch Size
|
|
reference: batch_size
|
|
trialSpec:
|
|
apiVersion: batch/v1
|
|
kind: Job
|
|
spec:
|
|
template:
|
|
spec:
|
|
containers:
|
|
- name: training-container
|
|
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:latest
|
|
command:
|
|
- "python3"
|
|
- "/opt/pytorch-mnist/mnist.py"
|
|
- "--epochs=${trialParameters.epochs}"
|
|
- "--batch-size=${trialParameters.batchSize}"
|
|
- "--lr=${trialParameters.learningRate}"
|
|
- "--momentum=${trialParameters.momentum}"
|
|
restartPolicy: Never
|