mirror of
https://github.com/hanzo-ml/katib.git
synced 2026-10-30 14:46:14 +00:00
55550f8df5
* Out-of-the-box support TrainJob Signed-off-by: Ram Lau <[email protected]> * Example for Pytorch Distributed Signed-off-by: Ram Lau <[email protected]> * Update examples/v1beta1/kubeflow-training-operator/trainjob-pytorch.yaml Co-authored-by: Andrey Velichkevich <[email protected]> Signed-off-by: Ram Lau <[email protected]> * Create folder for Trainer as suggested Signed-off-by: Ram Lau <[email protected]> * Movethe exmaple of trainjob to the new folder Signed-off-by: Ram Lau <[email protected]> * Ref the primaryContainerName to that of ClusterTrainingRuntime Signed-off-by: Ram Lau <[email protected]> * tenzen-y steps down from Katib approver role (#2561) Signed-off-by: Yuki Iwai <[email protected]> Signed-off-by: Ram Lau <[email protected]> * Set Default value for TrainJob Success, Failure Condition and PrimaryPodLabels in the trial Template Signed-off-by: Ram Lau <[email protected]> * Enchance Handling for default value of Success, Fail Cond & Pod Label Signed-off-by: Ram Lau <[email protected]> * Bug fix for default value condition Signed-off-by: Ram Lau <[email protected]> * code format by hack/update-gofmt.sh Signed-off-by: Ram Lau <[email protected]> * add TrainJob trial Resources to cert manager config Signed-off-by: Ram Lau <[email protected]> * add trainjob to controller rbac Signed-off-by: Ram Lau <[email protected]> * Grant JobSet permission to Katib controller Signed-off-by: Andrey Velichkevich <[email protected]> * Remove create/delete RBAC for TrainJob Signed-off-by: Andrey Velichkevich <[email protected]> * Fix docker build with libpcre2 Signed-off-by: Andrey Velichkevich <[email protected]> --------- Signed-off-by: Ram Lau <[email protected]> Signed-off-by: Yuki Iwai <[email protected]> Signed-off-by: Andrey Velichkevich <[email protected]> Co-authored-by: Andrey Velichkevich <[email protected]> Co-authored-by: Yuki Iwai <[email protected]>
60 lines
2.0 KiB
YAML
60 lines
2.0 KiB
YAML
---
|
|
apiVersion: config.kubeflow.org/v1beta1
|
|
kind: KatibConfig
|
|
init:
|
|
controller:
|
|
webhookPort: 8443
|
|
trialResources:
|
|
- TrainJob.v1alpha1.trainer.kubeflow.org
|
|
- Job.v1.batch
|
|
- TFJob.v1.kubeflow.org
|
|
- PyTorchJob.v1.kubeflow.org
|
|
- MPIJob.v1.kubeflow.org
|
|
- XGBoostJob.v1.kubeflow.org
|
|
runtime:
|
|
metricsCollectors:
|
|
- kind: StdOut
|
|
image: ghcr.io/kubeflow/katib/file-metrics-collector:latest
|
|
- kind: File
|
|
image: ghcr.io/kubeflow/katib/file-metrics-collector:latest
|
|
- kind: TensorFlowEvent
|
|
image: ghcr.io/kubeflow/katib/tfevent-metrics-collector:latest
|
|
resources:
|
|
limits:
|
|
memory: 1Gi
|
|
suggestions:
|
|
- algorithmName: random
|
|
image: ghcr.io/kubeflow/katib/suggestion-hyperopt:latest
|
|
- algorithmName: tpe
|
|
image: ghcr.io/kubeflow/katib/suggestion-hyperopt:latest
|
|
- algorithmName: grid
|
|
image: ghcr.io/kubeflow/katib/suggestion-optuna:latest
|
|
- algorithmName: hyperband
|
|
image: ghcr.io/kubeflow/katib/suggestion-hyperband:latest
|
|
- algorithmName: bayesianoptimization
|
|
image: ghcr.io/kubeflow/katib/suggestion-skopt:latest
|
|
- algorithmName: cmaes
|
|
image: ghcr.io/kubeflow/katib/suggestion-goptuna:latest
|
|
- algorithmName: sobol
|
|
image: ghcr.io/kubeflow/katib/suggestion-goptuna:latest
|
|
- algorithmName: multivariate-tpe
|
|
image: ghcr.io/kubeflow/katib/suggestion-optuna:latest
|
|
- algorithmName: enas
|
|
image: ghcr.io/kubeflow/katib/suggestion-enas:latest
|
|
resources:
|
|
limits:
|
|
memory: 400Mi
|
|
- algorithmName: darts
|
|
image: ghcr.io/kubeflow/katib/suggestion-darts:latest
|
|
- algorithmName: pbt
|
|
image: ghcr.io/kubeflow/katib/suggestion-pbt:latest
|
|
persistentVolumeClaimSpec:
|
|
accessModes:
|
|
- ReadWriteMany
|
|
resources:
|
|
requests:
|
|
storage: 5Gi
|
|
earlyStoppings:
|
|
- algorithmName: medianstop
|
|
image: ghcr.io/kubeflow/katib/earlystopping-medianstop:latest
|