Skip to content

Training: Main documentation update #153

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jul 23, 2025
Merged

Training: Main documentation update #153

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
fd2f944
Training CLI & SDK: example notebook and README update
Jul 23, 2025
4740ef9
Merge branch 'aws:main' into main-docs-update
rsareddy0329 Jul 23, 2025
ecaf9c3
Merge branch 'aws:main' into main-docs-update
rsareddy0329 Jul 23, 2025
af6cfa8
Update training cli example notebook
Jul 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 9 additions & 8 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,8 +158,8 @@ hyp create hyp-pytorch-job \
--version 1.0 \
--job-name test-pytorch-job \
--image pytorch/pytorch:latest \
--command '["python", "train.py"]' \
--args '["--epochs", "10", "--batch-size", "32"]' \
--command '[python, train.py]' \
--args '[--epochs=10, --batch-size=32]' \
--environment '{"PYTORCH_CUDA_ALLOC_CONF": "max_split_size_mb:32"}' \
--pull-policy "IfNotPresent" \
--instance-type ml.p4d.24xlarge \
Expand All @@ -170,8 +170,8 @@ hyp create hyp-pytorch-job \
--queue-name "training-queue" \
--priority "high" \
--max-retry 3 \
--volumes '["data-vol", "model-vol", "checkpoint-vol"]' \
--persistent-volume-claims '["shared-data-pvc", "model-registry-pvc"]' \
--volumes '[data-vol, model-vol, checkpoint-vol]' \
--persistent-volume-claims '[shared-data-pvc, model-registry-pvc]' \
--output-s3-uri s3://my-bucket/model-artifacts
```

Expand Down Expand Up @@ -257,9 +257,10 @@ Along with the CLI, we also have SDKs available that can perform the training an

```

from sagemaker.hyperpod import HyperPodPytorchJob
from sagemaker.hyperpod.job
import ReplicaSpec, Template, Spec, Container, Resources, RunPolicy, Metadata
from sagemaker.hyperpod.training import HyperPodPytorchJob
from sagemaker.hyperpod.training
import ReplicaSpec, Template, Spec, Containers, Resources, RunPolicy
from sagemaker.hyperpod.common.config import Metadata

# Define job specifications
nproc_per_node = "1" # Number of processes per node
Expand All @@ -274,7 +275,7 @@ replica_specs =
(
containers =
[
Container
Containers
(
# Container name
name="container-name",
Expand Down
24 changes: 22 additions & 2 deletions examples/training/CLI/training-e2e-cli.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,12 +17,31 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"source": "!hyp list-cluster --output table",
"id": "9df747dbfa211453"
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"id": "b30debba",
"source": "!hyp set-cluster-context --cluster-name <cluster-name>",
"id": "8db986d2b42a9e88"
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"source": "!hyperpod get-clusters"
"execution_count": null,
"source": [
"#verify the cluster context\n",
"!hyp get-cluster-context "
],
"id": "ba996d7dc8e128d5"
},
{
"metadata": {
Expand All @@ -46,6 +65,7 @@
"metadata": {},
"outputs": [],
"source": [
"#example command\n",
"!hyp create hyp-pytorch-job \\\n",
" --version 1.0 \\\n",
" --job-name test-pytorch-job-cli \\\n",
Expand Down
Loading