microsoft/finetuning
skills/microsoft-foundry/finetuning/SKILL.md
Fine-tune models on Azure AI 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: May 28, 2026, 6:31 AM38.2s34 files scanned
SKILL.md
- name:
- finetuning
- description:
- Fine-tune models on Azure AI 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 Azure AI 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),
1,320SKILL.mdUpdated Jul 26, 2026
microsoft/skills/azure-app-onboard/prepare
devops
VerifiedTrustedCommunity
# Prepare — Architecture Planning & Cost Estimation ## Quick Reference | Property | Value | |----------|-------| | Best for | Mapping app components to Azure services with cost estimation and quota validation | | Inputs | `prereq-output.json` + `context.json` from `.copilot-azure/sessions/{id}/` | | Outputs | `prepare-plan.json` written to session directory | | Parent | [azure-app-onboard](../SKILL.md) | ## When to Use This Skill Invoked by the `azure-app-onboard` orchestrator at Phase 2 whe
1,320SKILL.mdUpdated Jul 26, 2026
microsoft/skills/azure-app-onboard/deploy
testing
VerifiedTrustedCommunity
# Deploy — IaC Execution & Health Verification ## Quick Reference | Property | Value | |----------|-------| | Best for | Executing validated IaC against Azure, health-checking deployed resources | | Inputs | `prepare-plan.json` + `scaffold-manifest.json` from `.copilot-azure/sessions/{id}/` | | Outputs | `deploy-result.json` written to session directory | | Parent | [azure-app-onboard](../SKILL.md) | ## When to Use This Skill Invoked by the `azure-app-onboard` orchestrator at Phase 4 when `s
1,320SKILL.mdUpdated Jul 26, 2026
microsoft/azure-app-onboard
tools
VerifiedTrustedCommunity
End-to-end orchestrator: from a business idea, app idea, or existing app to running Azure deployment with cost estimates and pre-deploy approval. Analyzes your app, auto-detects the right Azure services, scaffolds infrastructure code, and deploys — tailored to your app, not a template. Handles moving existing apps to Azure without rewriting or with minimal changes. WHEN: bring your app to Azure, plan my app, cost to run, is my code ready to deploy, deploy my app to the cloud, deploy all my services, what Azure services do I need, plan my Azure deployment, deploy my new app to Azure, one-click deploy, I have an app and want it on Azure, migrate my app to Azure, help me get started, build an app, no code yet, starter project. DO NOT USE FOR: running azd up (use azure-deploy), optimizing existing costs (use azure-cost), code readiness checks only (use azure-app-onboard-prereq).
1,320SKILL.mdUpdated Jul 26, 2026