SFT TPU Single Host - #512
Draft
karajendran wants to merge 9 commits into
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary of Completed Work
\E2\80\A2 Built directly on top of peer PR feat: add sft maxtext single host on tpu #510 (origin/rl-add-maxtext-sft).
\E2\80\A2 Focused train.py on Gemma 3 4B (gemma3-4b / google/gemma-3-4b-it) by default, while supporting dynamic environment overrides. Cleaned up all emojis from logs and print statements.
\E2\80\A2 Configured Kustomize overlay in (kustomization.yaml, patch-env.yaml, patch-nodeselector.yaml, patch-resources.yaml).
\E2\80\A2 mlflow.tf: Added mlflow.tf to deploy MLflow tracking server to GKE via Terraform.
\E2\80\A2 Service Name Consistency: Unified MLflow service name to mlflow-service across manifests, Python scripts, and documentation.
\E2\80\A2 Workload Identity GCS Access: Added roles/storage.objectAdmin IAM binding in storage.tf.
\E2\80\A2 GCS gs:// Path Check: Implemented path_exists() using google.cloud.storage.Client in train.py.
\E2\80\A2 Provider Version & Docker Workdir: Upgraded Terraform Google provider to 7.6.0 in versions.tf and added WORKDIR /workspace in Dockerfile.
\E2\80\A2 Comprehensive tutorial documentation in README.md covering both automated execution and step-by-step batch job conversion/training workflows.