ai-ml/mix-train-and-inference/workloads/fine-tune-l4.yaml

# Copyright 2024 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# [START gke_ai_ml_mix_train_and_inference_workloads_fine_tune_l4]
apiVersion: v1
kind: Service
metadata:
  name: headless-svc-l4
spec:
  clusterIP: None # clusterIP must be None to create a headless service
  selector:
    job-name: finetune-gemma-l4 # must match Job name
---
apiVersion: batch/v1
kind: Job
metadata:
  name: finetune-gemma-l4
  labels:
    kueue.x-k8s.io/queue-name: lq
spec:
  backoffLimit: 4
  completions: 2
  parallelism: 2
  completionMode: Indexed
  suspend: true # Set to true to allow Kueue to control the Job when it starts
  template:
    metadata:
      labels:
        app: finetune-job
      annotations:
        gke-gcsfuse/volumes: "true"
        gke-gcsfuse/memory-limit: "35Gi"
    spec:
      priorityClassName: low-priority-preempting
      containers:
      - name: gpu-job
        imagePullPolicy: Always
        image: us-docker.pkg.dev/google-samples/containers/gke/gemma-fine-tuning:v1.0.0
        ports:
        - containerPort: 29500
        resources:
          requests:
            nvidia.com/gpu: "2"
          limits:
            nvidia.com/gpu: "2"
        command:
        - bash
        - -c
        - |
          accelerate launch \
          --config_file fsdp_config.yaml \
          --debug \
          --main_process_ip finetune-gemma-l4-0.headless-svc-l4 \
          --main_process_port 29500 \
          --machine_rank ${JOB_COMPLETION_INDEX} \
          --num_processes 4 \
          --num_machines 2 \
          fine_tune.py
        env:
        - name: "EXPERIMENT"
          value: "finetune-experiment"
        - name: "TRAINING_DATASET_BUCKET"
          value: <TRAINING_BUCKET>
        - name: "TRAINING_DATASET_PATH"
          value: "training"
        - name: MODEL_NAME
          value: "google/gemma-2-9b-it"
        - name: NEW_MODEL
          value: "gemma-ft"
        - name: MODEL_PATH
          value: "/model-data/model-gemma2/experiment"
        - name: EPOCHS
          value: "1"
        - name: CHECKPOINT_SAVE_STEPS
          value: "1"
        - name: HF_TOKEN
          valueFrom:
            secretKeyRef:
              name: hf-secret
              key: hf_api_token
        volumeMounts:
        - mountPath: /dev/shm
          name: dshm
        - name: gcs-fuse-csi-ephemeral
          mountPath: /model-data
          readOnly: false
      nodeSelector:
        cloud.google.com/gke-accelerator: nvidia-l4
      restartPolicy: OnFailure
      serviceAccountName: default
      subdomain: headless-svc-l4
      terminationGracePeriodSeconds: 60
      volumes:
      - name: dshm
        emptyDir:
          medium: Memory
      - name: gcs-fuse-csi-ephemeral
        csi:
          driver: gcsfuse.csi.storage.gke.io
          volumeAttributes:
            bucketName: <MODEL_BUCKET>
            mountOptions: "implicit-dirs"
            gcsfuseLoggingSeverity: warning

# [END gke_ai_ml_mix_train_and_inference_workloads_fine_tune_l4]