finetuning

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).

Jump to install Review files

Repository: microsoft/skills
Last source activity: August 7, 2026 at 11:17
Detected SKILL.md language: English
Stars: 3,148
Forks: 355

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/microsoft/skills/tree/main/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/microsoft/skills --skill finetuning

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

34 files

SKILL.md

Source instructions · Read-only preview

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
metadata: {"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](workflows/quickstart.md) | | **Full pipeline** | [workflows/full-pipeline.md](workflows/full-pipeline.md) | | **Create data** | [workflows/dataset-creation.md](workflows/dataset-creation.md) | | **Iterate** | [workflows/iterative-training.md](workflows/iterative-training.md) | | **Diagnose** | [workflows/diagnose-poor-results.md](workflows/diagnose-poor-results.md) | ## References | Topic | File | |-------|------| | SFT vs DPO vs RFT | [references/training-types.md](references/training-types.md) | | Hyperparameters | [references/hyperparameters.md](references/hyperparameters.md) | | Data formats | [references/dataset-formats.md](references/dataset-formats.md) | | Grader design (RFT) | [references/grader-design.md](references/grader-design.md) | | Reward hacking | [references/reward-hacking.md](references/reward-hacking.md) | | Agentic RFT (tools) | [references/agentic-rft.md](references/agentic-rft.md) | | Deployment | [references/deployment.md](references/deployment.md) | | Training curves | [references/training-curves.md](references/training-curves.md) | | Evaluation | [references/evaluation.md](references/evaluation.md) | | Vision fine-tuning | [references/vision-fine-tuning.md](references/vision-fine-tuning.md) | | Large file uploads | [references/large-file-uploads.md](references/large-file-uploads.md) | | Platform gotchas | [references/platform-gotchas.md](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 1. **Always baseline first** — evaluate the base model before fine-tuning 2. **Validate data** before submitting — run `scripts/validate/validate_sft.py` 3. **Calibrate RFT graders** — target 25-50% failure rate on the base model 4. **Evaluate checkpoints** — don't blindly deploy the final one 5. **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 |

View on GitHub

Back to search Back to installation

microsoft-foundry

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

2026-10-23

azure-kubernetes-app-deploy

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.

2026-10-21

azure-kubernetes

Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters. Covers Day-0 checklist, SKU selection (Automatic vs Standard), networking options (private API server, Azure CNI Overlay, egress configuration), security, and operations (autoscaling, upgrade strategy, cost analysis). WHEN: create AKS environment, provision AKS, enable AKS observability, design AKS networking, choose AKS SKU, secure AKS, optimize AKS, AKS spot nodes, AKS cluster-autoscaler, rightsize AKS pod, pod rightsizing, over-provisioned AKS pod, pod resource requests and limits, Vertical Pod Autoscaler, VPA recommendations.

2026-10-21

View all from this repository

finetuning

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository