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]>
120 lines
4.0 KiB
YAML
120 lines
4.0 KiB
YAML
---
|
|
apiVersion: kubeflow.org/v1beta1
|
|
kind: Experiment
|
|
metadata:
|
|
namespace: kubeflow
|
|
name: xgboostjob-lightgbm
|
|
spec:
|
|
objective:
|
|
type: maximize
|
|
goal: 0.99
|
|
objectiveMetricName: valid_1 auc
|
|
additionalMetricNames:
|
|
- valid_1 binary_logloss
|
|
- training auc
|
|
- training binary_logloss
|
|
metricsCollectorSpec:
|
|
source:
|
|
filter:
|
|
metricsFormat:
|
|
- "(\\w+\\s\\w+)\\s:\\s((-?\\d+)(\\.\\d+)?)"
|
|
algorithm:
|
|
algorithmName: random
|
|
parallelTrialCount: 2
|
|
maxTrialCount: 6
|
|
maxFailedTrialCount: 3
|
|
parameters:
|
|
- name: lr
|
|
parameterType: double
|
|
feasibleSpace:
|
|
min: "0.01"
|
|
max: "0.1"
|
|
- name: num-leaves
|
|
parameterType: int
|
|
feasibleSpace:
|
|
min: "50"
|
|
max: "60"
|
|
step: "1"
|
|
trialTemplate:
|
|
primaryContainerName: xgboost
|
|
trialParameters:
|
|
- name: learningRate
|
|
description: Learning rate for the training model
|
|
reference: lr
|
|
- name: numberLeaves
|
|
description: Number of leaves for one tree
|
|
reference: num-leaves
|
|
trialSpec:
|
|
apiVersion: kubeflow.org/v1
|
|
kind: XGBoostJob
|
|
spec:
|
|
xgbReplicaSpecs:
|
|
Master:
|
|
replicas: 1
|
|
restartPolicy: Never
|
|
template:
|
|
spec:
|
|
containers:
|
|
- name: xgboost
|
|
image: ghcr.io/kubeflow/katib/xgboost-lightgbm:1.0
|
|
ports:
|
|
- containerPort: 9991
|
|
name: xgboostjob-port
|
|
imagePullPolicy: Always
|
|
args:
|
|
- --job_type=Train
|
|
- --metric=binary_logloss,auc
|
|
- --learning_rate=${trialParameters.learningRate}
|
|
- --num_leaves=${trialParameters.numberLeaves}
|
|
- --num_trees=100
|
|
- --boosting_type=gbdt
|
|
- --objective=binary
|
|
- --metric_freq=1
|
|
- --is_training_metric=true
|
|
- --max_bin=255
|
|
- --data=data/binary.train
|
|
- --valid_data=data/binary.test
|
|
- --tree_learner=feature
|
|
- --feature_fraction=0.8
|
|
- --bagging_freq=5
|
|
- --bagging_fraction=0.8
|
|
- --min_data_in_leaf=50
|
|
- --min_sum_hessian_in_leaf=50
|
|
- --is_enable_sparse=true
|
|
- --use_two_round_loading=false
|
|
- --is_save_binary_file=false
|
|
Worker:
|
|
replicas: 2
|
|
restartPolicy: ExitCode
|
|
template:
|
|
spec:
|
|
containers:
|
|
- name: xgboost
|
|
image: ghcr.io/kubeflow/katib/xgboost-lightgbm:1.0
|
|
ports:
|
|
- containerPort: 9991
|
|
name: xgboostjob-port
|
|
imagePullPolicy: Always
|
|
args:
|
|
- --job_type=Train
|
|
- --metric=binary_logloss,auc
|
|
- --learning_rate=${trialParameters.learningRate}
|
|
- --num_leaves=${trialParameters.numberLeaves}
|
|
- --num_trees=100
|
|
- --boosting_type=gbdt
|
|
- --objective=binary
|
|
- --metric_freq=1
|
|
- --is_training_metric=true
|
|
- --max_bin=255
|
|
- --data=data/binary.train
|
|
- --valid_data=data/binary.test
|
|
- --tree_learner=feature
|
|
- --feature_fraction=0.8
|
|
- --bagging_freq=5
|
|
- --bagging_fraction=0.8
|
|
- --min_data_in_leaf=50
|
|
- --min_sum_hessian_in_leaf=50
|
|
- --is_enable_sparse=true
|
|
- --use_two_round_loading=false
|
|
- --is_save_binary_file=false
|