skillZs
LIVE SKILL TAGS
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
REAL INSTALL DATA
← back to all skills
microsoft/azure-skills458k installs

finetuning

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).

How do I install this agent skill?

npx skills add https://github.com/microsoft/azure-skills --skill microsoft-foundry
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill provides a robust and comprehensive toolkit for managing the lifecycle of AI agents on the Microsoft Foundry platform. It follows established cloud development practices, using official Microsoft tools and repositories to automate deployment, evaluation, and troubleshooting workflows. While the skill possesses powerful capabilities for managing cloud infrastructure and sensitive logs, these are central to its intended purpose as a developer management tool.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 2 issues

  • ZeroLeakswarn

    Scan incomplete

What does this agent skill do?

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

StageGuide
Quick startworkflows/quickstart.md
Full pipelineworkflows/full-pipeline.md
Create dataworkflows/dataset-creation.md
Iterateworkflows/iterative-training.md
Diagnoseworkflows/diagnose-poor-results.md

References

TopicFile
SFT vs DPO vs RFTreferences/training-types.md
Hyperparametersreferences/hyperparameters.md
Data formatsreferences/dataset-formats.md
Grader design (RFT)references/grader-design.md
Reward hackingreferences/reward-hacking.md
Agentic RFT (tools)references/agentic-rft.md
Deploymentreferences/deployment.md
Training curvesreferences/training-curves.md
Evaluationreferences/evaluation.md
Vision fine-tuningreferences/vision-fine-tuning.md
Large file uploadsreferences/large-file-uploads.md
Platform gotchasreferences/platform-gotchas.md

Scripts

ScriptPurpose
scripts/submit_training.pySubmit SFT/DPO/RFT jobs
scripts/monitor_training.pyPoll job until completion
scripts/calibrate_grader.pyFind optimal RFT pass_threshold
scripts/check_training.pyAnalyze curves, list checkpoints
scripts/deploy_model.pyDeploy via ARM REST API
scripts/evaluate_model.pyLLM judge evaluation
scripts/convert_dataset.pyConvert between SFT/DPO/RFT formats
scripts/generate_distillation_data.pyGenerate synthetic training data
scripts/score_dataset.pyQuality scoring on training data
scripts/cleanup.pyDelete 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

TaskCommand
Validate SFT datapython scripts/validate/validate_sft.py data.jsonl
Submit SFT jobpython scripts/submit_training.py --model gpt-4.1-mini --training-file train.jsonl --validation-file val.jsonl --type sft
Monitor jobpython scripts/monitor_training.py --job-id ftjob-xxx
Analyze curvespython scripts/check_training.py --job-id ftjob-xxx
Deploy modelpython scripts/deploy_model.py --model-id ft:gpt-4.1-mini:... --name my-eval
Evaluate modelpython scripts/evaluate_model.py --deployment-name my-eval --test-file test.jsonl

Error Handling

ErrorCauseFix
"API version not supported"Older openai SDK on /v1/ endpointUpgrade to openai>=1.0
"does not support fine-tuning with Standard TrainingType"OSS model needs globalStandardUse --use-rest flag or script auto-falls back
Job stuck in post-training evalUnder-provisioned tool endpoint (RFT)Scale to S2+, enable Always On
"DeploymentNotReady" after ARM succeedsARM/data-plane race conditionDelete and recreate deployment, wait 5 min
Content safety block at deploymentPII-dense training dataRemove problematic document types

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/microsoft/azure-skills/microsoft-foundry">View finetuning on skillZs</a>