microsoft/finetuning
skills/microsoft-foundry/finetuning/SKILL.md
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
$ install --global
skillsauthnpx skillsauth add microsoft/azure-skills finetuningInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Aug 15, 2026, 4:21 AM193.5s34 files scanned
SKILL.md
- name:
- finetuning
- description:
- Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
- license:
- MIT
- author:
- Microsoft
- version:
- 0.0.0-placeholder
Fine-Tuning on Microsoft Foundry
Fine-tune models using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset prep, training, deployment, and evaluation.
When to Use
Use this sub-skill when the user asks about:
- Fine-tuning a model (SFT, DPO, or RFT)
- Preparing, validating, or formatting training data
- Submitting, monitoring, or diagnosing training jobs
- Calibrating graders or pass thresholds for RFT
- Deploying or evaluating a fine-tuned model
- Choosing between training types (SFT vs DPO vs RFT)
- Distillation, synthetic data generation, or dataset quality scoring
- Large file uploads for training data
- Cleaning up fine-tuning resources (files, deployments)
Do NOT use for: General model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
Workflows
| Stage | Guide | |-------|-------| | Quick start | workflows/quickstart.md | | Full pipeline | workflows/full-pipeline.md | | Create data | workflows/dataset-creation.md | | Iterate | workflows/iterative-training.md | | Diagnose | workflows/diagnose-poor-results.md |
References
| Topic | File | |-------|------| | SFT vs DPO vs RFT | references/training-types.md | | Hyperparameters | references/hyperparameters.md | | Data formats | references/dataset-formats.md | | Grader design (RFT) | references/grader-design.md | | Reward hacking | references/reward-hacking.md | | Agentic RFT (tools) | references/agentic-rft.md | | Deployment | references/deployment.md | | Training curves | references/training-curves.md | | Evaluation | references/evaluation.md | | Vision fine-tuning | references/vision-fine-tuning.md | | Large file uploads | references/large-file-uploads.md | | Platform gotchas | references/platform-gotchas.md |
Scripts
| Script | Purpose |
|--------|---------|
| scripts/submit_training.py | Submit SFT/DPO/RFT jobs |
| scripts/monitor_training.py | Poll job until completion |
| scripts/calibrate_grader.py | Find optimal RFT pass_threshold |
| scripts/check_training.py | Analyze curves, list checkpoints |
| scripts/deploy_model.py | Deploy via ARM REST API |
| scripts/evaluate_model.py | LLM judge evaluation |
| scripts/convert_dataset.py | Convert between SFT/DPO/RFT formats |
| scripts/generate_distillation_data.py | Generate synthetic training data |
| scripts/score_dataset.py | Quality scoring on training data |
| scripts/cleanup.py | Delete old files and deployments |
| scripts/validate/ | Data validators (SFT, DPO, RFT) + stats |
Rules
- Always baseline first — evaluate the base model before fine-tuning
- Validate data before submitting — run
scripts/validate/validate_sft.py - Calibrate RFT graders — target 25-50% failure rate on the base model
- Evaluate checkpoints — don't blindly deploy the final one
- Measure token cost alongside accuracy when comparing models
Quick Reference
| Task | Command |
|------|---------|
| Validate SFT data | python scripts/validate/validate_sft.py data.jsonl |
| Submit SFT job | python scripts/submit_training.py --model gpt-4.1-mini --training-file train.jsonl --validation-file val.jsonl --type sft |
| Monitor job | python scripts/monitor_training.py --job-id ftjob-xxx |
| Analyze curves | python scripts/check_training.py --job-id ftjob-xxx |
| Deploy model | python scripts/deploy_model.py --model-id ft:gpt-4.1-mini:... --name my-eval |
| Evaluate model | python scripts/evaluate_model.py --deployment-name my-eval --test-file test.jsonl |
Error Handling
| Error | Cause | Fix |
|-------|-------|-----|
| "API version not supported" | Older openai SDK on /v1/ endpoint | Upgrade to openai>=1.0 |
| "does not support fine-tuning with Standard TrainingType" | OSS model needs globalStandard | Use --use-rest flag or script auto-falls back |
| Job stuck in post-training eval | Under-provisioned tool endpoint (RFT) | Scale to S2+, enable Always On |
| "DeploymentNotReady" after ARM succeeds | ARM/data-plane race condition | Delete and recreate deployment, wait 5 min |
| Content safety block at deployment | PII-dense training data | Remove problematic document types |
Related Skills
microsoft/skills/azure-app-onboard/scaffold
development
VerifiedTrustedCommunity
# Azure App Onboard Scaffold — IaC Generation + Self-Review Generate deployment-ready infrastructure code from an architecture plan, verify it with adversarial self-review, and bridge to validation — all without deploying. ## Quick Reference | Property | Value | |----------|-------| | Parent | [azure-app-onboard](../SKILL.md) | | Best for | Turning `prepare-plan.json` service list into Bicep templates with secure-by-default patterns | | Inputs | `prepare-plan.json` (services, naming, quotas),
1,398SKILL.mdUpdated Jul 26, 2026
microsoft/azure-cloud-migrate
development
VerifiedTrustedCommunity
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud Run migration, Fargate to ACA, ECS/Kubernetes/GKE/EKS to Container Apps, Spring Boot to Container Apps, cross-cloud migration.
1,398SKILL.mdUpdated Apr 7, 2026
microsoft/azure-kubernetes-app-deploy
development
VerifiedTrustedCommunity
Use when deploying an existing web application or API to an already-running Azure Kubernetes Service cluster. Detects the framework, generates a Dockerfile and Kubernetes manifests, validates against AKS Deployment Safeguards, and deploys with verification. WHEN: deploy app to AKS, deploy to existing AKS cluster, containerize app for Kubernetes, generate K8s manifests for Azure, set up CI/CD for AKS, my AKS deployment is failing safeguard checks, I have a Django/Express/Spring Boot app to run on AKS. DO NOT USE FOR: creating or provisioning an AKS cluster (use azure-kubernetes), assessing migration to AKS Automatic (use azure-kubernetes-automatic-readiness), or deploying to non-AKS targets like Web Apps, Container Apps, or Functions.
1,379SKILL.mdUpdated Aug 15, 2026
microsoft/customize
testing
VerifiedTrustedCommunity
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
1,379SKILL.mdUpdated Apr 7, 2026