mirror of
https://github.com/hanzo-ml/katib.git
synced 2026-10-30 14:46:14 +00:00
Rishit DagliandGitHub
b3573e745c
* Fix missing document start warnings * Fix too few spaces before comment warning
97 lines
2.7 KiB
YAML
97 lines
2.7 KiB
YAML
---
|
|
apiVersion: kubeflow.org/v1beta1
|
|
kind: Experiment
|
|
metadata:
|
|
namespace: kubeflow
|
|
name: mpijob-horovod
|
|
spec:
|
|
objective:
|
|
type: minimize
|
|
goal: 0.01
|
|
objectiveMetricName: loss
|
|
algorithm:
|
|
algorithmName: random
|
|
parallelTrialCount: 2
|
|
maxTrialCount: 6
|
|
maxFailedTrialCount: 3
|
|
parameters:
|
|
- name: lr
|
|
parameterType: double
|
|
feasibleSpace:
|
|
min: "0.001"
|
|
max: "0.003"
|
|
- name: num-steps
|
|
parameterType: int
|
|
feasibleSpace:
|
|
min: "50"
|
|
max: "150"
|
|
step: "10"
|
|
trialTemplate:
|
|
primaryPodLabels:
|
|
mpi-job-role: launcher
|
|
primaryContainerName: mpi-launcher
|
|
successCondition: status.conditions.#(type=="Succeeded")#|#(status=="True")#
|
|
failureCondition: status.conditions.#(type=="Failed")#|#(status=="True")#
|
|
trialParameters:
|
|
- name: learningRate
|
|
description: Learning rate for the training model
|
|
reference: lr
|
|
- name: numberSteps
|
|
description: Number of training steps
|
|
reference: num-steps
|
|
trialSpec:
|
|
apiVersion: kubeflow.org/v1
|
|
kind: MPIJob
|
|
spec:
|
|
slotsPerWorker: 1
|
|
cleanPodPolicy: Running
|
|
mpiReplicaSpecs:
|
|
Launcher:
|
|
replicas: 1
|
|
template:
|
|
spec:
|
|
containers:
|
|
- image: docker.io/kubeflow/mpi-horovod-mnist
|
|
name: mpi-launcher
|
|
command:
|
|
- mpirun
|
|
args:
|
|
- -np
|
|
- "2"
|
|
- --allow-run-as-root
|
|
- -bind-to
|
|
- none
|
|
- -map-by
|
|
- slot
|
|
- -x
|
|
- LD_LIBRARY_PATH
|
|
- -x
|
|
- PATH
|
|
- -mca
|
|
- pml
|
|
- ob1
|
|
- -mca
|
|
- btl
|
|
- ^openib
|
|
- python
|
|
- /examples/tensorflow_mnist.py
|
|
- --lr
|
|
- ${trialParameters.learningRate}
|
|
- --num-steps
|
|
- ${trialParameters.numberSteps}
|
|
resources:
|
|
limits:
|
|
cpu: 500m
|
|
memory: 2Gi
|
|
Worker:
|
|
replicas: 2
|
|
template:
|
|
spec:
|
|
containers:
|
|
- image: docker.io/kubeflow/mpi-horovod-mnist
|
|
name: mpi-worker
|
|
resources:
|
|
limits:
|
|
cpu: 500m
|
|
memory: 4Gi
|