diff --git a/dlrover/examples/troch_debug_job.yaml b/dlrover/examples/torch_debug_job.yaml similarity index 79% rename from dlrover/examples/troch_debug_job.yaml rename to dlrover/examples/torch_debug_job.yaml index ccd7cba5a..ea26466db 100644 --- a/dlrover/examples/troch_debug_job.yaml +++ b/dlrover/examples/torch_debug_job.yaml @@ -1,7 +1,7 @@ apiVersion: elastic.iml.github.io/v1alpha1 kind: ElasticJob metadata: - name: torch-mnist + name: torch-mnist-debug namespace: dlrover spec: distributionStrategy: AllreduceStrategy @@ -15,8 +15,8 @@ spec: containers: - name: main # yamllint disable-line rule:line-length - image: registry.cn-hangzhou.aliyuncs.com/intell-ai/dlrover:torch201-mnist-test - imagePullPolicy: Always + image: easydl/dlrover-train:test + imagePullPolicy: Never command: - /bin/bash - -c @@ -38,5 +38,5 @@ spec: restartPolicy: Never containers: - name: main - imagePullPolicy: Always - image: registry.cn-hangzhou.aliyuncs.com/intell-ai/dlrover:test + imagePullPolicy: Never + image: easydl/dlrover-master:test diff --git a/docs/developer_guide.md b/docs/developer_guide.md index f8ca4d346..a89c2be49 100644 --- a/docs/developer_guide.md +++ b/docs/developer_guide.md @@ -200,7 +200,7 @@ docker build -t easydl/dlrover-master:test -f docker/Dockerfile . **Build the training image of PyTorch models.** ```bash -docker build -t easydl/dlrover-master:test -f docker/pytorch/mnist.dockerfile . +docker build -t easydl/dlrover-train:test -f docker/pytorch/mnist.dockerfile . ``` ### 5. Submit an ElasticJob to test your images.