AutoGineer
Generated banner for Finetuning
Generated logo for Finetuning

Finetuning

AWS LabsOfficialPublished by AWS Labs

  • Skill
  • Workflow
  • Data and AI
  • Apache-2.0
  • Low risk
  • Has scripts
Download ZIP

From the author

Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom prompt creation.
— the description by AWS Labs

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured workflow to generate code for fine-tuning machine learning models on AWS SageMaker. It supports multiple training techniques including SFT, DPO, RLVR, and RLAIF. The skill ensures that all prerequisites—such as use case specifications, model selection, and environment configuration—are met before generating the necessary Python scripts or Jupyter notebooks. It also handles EULA acceptance for specific models and provides options for executing training jobs and monitoring their status.

What it does

  • Generates standardized training code for SFT, DPO, RLVR, and RLAIF techniques.
  • Configures SageMaker serverless training jobs with appropriate model and dataset parameters.
  • Manages EULA review and acceptance for restricted base models.
  • Supports creation of custom reward functions for RLVR workflows.
  • Provides options to run training jobs as scripts or within notebooks.
  • Monitors training job status and reports performance metrics upon completion.

When to use it

  • When the user requests to start training or fine-tune a model.
  • When the project plan reaches the fine-tuning phase.
  • When you need to perform a subsequent round of fine-tuning on an already customized model.

Advantages

  • Ensures consistent code structure and dependency management across projects.
  • Automates the configuration of complex SageMaker training parameters.
  • Provides a safe, step-by-step process that validates prerequisites before execution.
  • Offers flexible execution modes (notebook vs. script) to suit user preferences.

Usage examples

“I'm ready to train my model using SFT.”
The agent verifies prerequisites, selects the SFT template, configures the SageMaker environment, and generates the training notebook or script.
“Can you help me fine-tune this model with RLVR?”
The agent guides the user through creating a reward function or providing an existing ARN, then generates the RLVR training code.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/awslabs/finetuning/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip finetuning.zip -d .agents/skills

Documentation by AWS Labs

Prerequisites

Before starting this workflow, verify:

  1. A use_case_spec.md file exists

    • If missing: Activate the use-case-specification skill first, then resume

    • DON'T EVER offer to create a use case spec without activating the use-case-specification skill.

  2. A fine-tuning technique (SFT, DPO, RLVR, RLAIF, or CPT/RFT (for Nova)) and base model have already been selected

    • If missing: Activate the model-selection and/or finetuning-technique skills to collect what's missing, then resume

    • Don't make recommendations on the spot. You MUST activate the appropriate skill.

  3. A base model name available on SageMakerHub has been identified

    • If missing: Activate the model-selection skill to get it

    • Important: Only use the model name that model-selection retrieves, as it may differ from other commonly used names for the same model

  4. The SDK environment has been verified (SDK version, region, execution role)

    • If not done: Activate the sdk-getting-started skill first, then resume

  5. A training dataset uploaded to a bucket in the environment's default region.

    • If not met: Help the user upload the dataset to the correct S3

Critical Rules

Code Generation Rules

  • ✅ Use EXACTLY the imports shown in each code template

  • ❌ Do NOT add additional imports even if they seem helpful

  • ❌ Do NOT create variables before they're needed in that section

  • 📋 Copy the code structure precisely - no improvisation

  • 🎯 Follow the minimal code principle strictly

  • ✅ When writing code, make sure the indentation and f strings are correct

User Communication Rules

  • ❌ NEVER offer to move on to a downstream skill while training is in progress (logically impossible)

  • ❌ NEVER set ACCEPT_EULA to True without explicit user confirmation in the conversation

  • ✅ Always mention both the number AND title of sections you reference

  • ✅ If user asks how to run (notebook): If run_cell is available, offer to run it. Otherwise, tell them to run cells one by one (mention ipykernel requirement).

  • ✅ If user asks how to run (script): Tell them to run with python3 <script>.py

Workflow

1. Code Generation Setup

1.1 Directory Setup

  1. Identify project directory from conversation context

    • If unclear (multiple relevant directories exist) → Ask user which folder to use

    • If no project directory exists → activate the directory-management skill to set one up

⏸ Wait for user.

1.2 Select Code Template

Read references/code_output_guide.md for output format rules, then read the code template matching the finetuning strategy:

  • SFT → code_templates/sft.py

  • DPO → code_templates/dpo.py

  • RLVR → code_templates/rlvr.py

  • RLAIF with built-in rewards → code_templates/rlaif_builtin.py

  • RLAIF with custom prompt → code_templates/rlaif_custom_prompt.py

The template is a Python file where each # Cell N: Label comment marks the start of a new section. Split on these markers — everything between one marker and the next becomes one unit of output.

1.3 Generate Code

  1. Write the code from the template following the rules in code_output_guide.md

  2. Use same order, dependencies, and imports as the template

  3. DO NOT improvise or add extra code

  4. If the model is NOT a Meta/Llama model (model ID does NOT start with meta-):

    • Omit the ACCEPT_EULA = False line from the config cell

    • Omit the accept_eula=ACCEPT_EULA, line from the trainer call

  5. If the model is from the Nova family, omit any code containing max_epochs or lr_warmup_steps_ratio from the Configure Trainer section and the Hyperparameter Overrides section

1.4 Auto-Generate Configuration Values

In the 'Setup & Credentials' cell, populate:

  1. BASE_MODEL

    • Use the exact SageMakerHub model name from context

  2. MODEL_PACKAGE_GROUP_NAME

    • Generate from use case (read use_case_spec.md if needed)

    • Format rules:

      • Lowercase, alphanumeric with hyphens only

      • 1-63 characters

      • Pattern: [a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}

      • Example: "Customer Support Chatbot" → customer-support-chatbot-v1

  3. Save notebook

2. RLVR Reward Function (for RLVR only, skip this section if technique is SFT or DPO)

2.1 Check Reward Function Status

  • Ask if user has a reward function already, or would like help creating one.

    • If user says they have one → Ask for the SageMaker Hub Evaluator ARN. Only proceed to Section 2.3 once the user provides a valid Evaluator ARN. If they don't have it registered as a SageMaker Hub Evaluator, continue to 2.2.

    • If user says they do not have one → Continue to 2.2

2.2 Generate Reward Function From Template

  1. Follow workflow in references/rlvr_reward_function.md section "Helping Users Create Custom Reward Functions"

2.3 Set CUSTOM_REWARD_FUNCTION value

  1. Set the value for CUSTOM_REWARD_FUNCTION in the Notebook with the ARN of the reward function (either given directly by the user, or from the function generation code as evaluator.arn).

3. RLAIF (for RLAIF only, skip this section if technique is not RLAIF)

Read references/rlaif_guide.md and follow its instructions.

4. EULA review and acceptance

  1. Look up the official license link for the selected base model from references/eula_links.md

  2. Display the license to the user following the phrasing in references/eula_links.md. For OSS models: "This model is licensed under {License}. Please review the license terms here: {URL}." For Nova models: "This model is subject to the AWS Service Terms: {URL}."

  3. Check if the selected base model is a Meta/Llama model (model ID starts with meta-)

    • If Meta/Llama: Tell the user they must read and agree to the EULA before using this model. Ask: "Do you accept the license terms? (yes/no)". If the user confirms, set ACCEPT_EULA = True and uncomment accept_eula=ACCEPT_EULA in the generated notebook. If the user declines, leave ACCEPT_EULA = False and warn that training will fail without acceptance.

    • If non-Meta: Inform the user of the license for their awareness. No code-level action needed — the ACCEPT_EULA variable and accept_eula parameter should already be omitted from the notebook (see Step 1.3).

5. Post-Generation

After generating the code, offer to run it. Training can take hours depending on your dataset and model.

Notebook mode: If run_cell is available, offer to run the cells. Otherwise tell the user to run cells themselves.

Script mode: Present the user with options:

"Would you like me to:

  1. Leave it to you — run with python scripts/[script_name]

  2. Run it and wait until it's done

  3. Start it but don't wait — we can check status later"

  • Option 1: Done. Wait for user to come back.

  • Option 2: Execute the script as-is. trainer.train(wait=True) blocks until complete. Report final status.

  • Option 3: Change wait=True to wait=False in the script, execute, report the training job name.

Checking status:

  • describe-training-job --training-job-name NAME → TrainingJobStatus, FailureReason, SecondaryStatusTransitions

  • For model package ARN after completion: list-model-packages --model-package-group-name GROUP_NAME --sort-by CreationTime --sort-order Descending --max-results 1

Showing results after completion:

  • Use scripts/mlflow_reference.py as the pattern to query MLflow metrics

  • Present loss by epoch as a text table (total_loss, val_eval_total_loss for SFT; rewards/margins for DPO; critic/rewards/mean for RLVR)

CRITICAL:

  • DON'T suggest moving to next steps before training completes

  • DON'T elaborate on the next steps unless the user specifically asks you about them.

6. Continuous Customization

If the user wants to finetune a model they had already customized, follow the instructions in references/continuous_customization.md

References

  • rlvr_reward_function.md - Lambda reward function creation guide (RLVR only)

  • templates/rlvr_reward_function_source_template.py - Lambda reward function source template for open-weights models (RLVR only)

  • templates/nova_rlvr_reward_function_source_template.py - Lambda reward function source template for Nova 2.0 Lite (RLVR only)

  • code_templates/sft.py - Complete notebook template for Supervised Fine-Tuning (OSS path)

  • code_templates/dpo.py - Complete notebook template for Direct Preference Optimization (OSS path)

  • code_templates/rlvr.py - Complete notebook template for Reinforcement Learning from Verifiable Rewards (OSS path)

  • references/continuous_customization.md - Instructions on fine-tuning an already fine-tuned model.

  • rlaif_guide.md - instructions on RLAIF finetuning options

  • rlaif_builtin.py - Code template for RLAIF with built-in judge prompt

  • rlaif_custom_prompt.py - Code template for RLAIF with custom judge prompt

Files

code_templates/rlaif_builtin.py

# RLAIF (Reinforcement Learning from AI Feedback) Template — Builtin Reward Prompt

# Cell 0 [markdown]: Fine-Tuning

# Cell 1: Install Dependencies

%pip install --upgrade 'sagemaker>=3.7.1,<4.0' boto3 -q  # NOTEBOOK_ONLY

# Cell 2: Setup & Credentials

import boto3
import json
from pathlib import Path
from botocore.exceptions import ClientError
from sagemaker.ai_registry.dataset import DataSet
from sagemaker.core.resources import ModelPackageGroup
from sagemaker.core.helper.session_helper import Session, get_execution_role
from sagemaker.core import Attribution, set_attribution
from sagemaker.train.rlaif_trainer import RLAIFTrainer
from sagemaker.train.common import TrainingType

set_attribution(Attribution.SAGEMAKER_AGENT_PLUGIN)

# Setup
sm_client = boto3.Session().client("sagemaker")
sagemaker_session = Session(sagemaker_client=sm_client)
bucket = sagemaker_session.default_bucket()

# Configuration - USER please fill in these fields with your information:

BASE_MODEL = "" # Sagemaker Hub model id
TRAINING_DATA_S3 = ""  # S3 path
S3_OUTPUT_PATH = f"s3://{bucket}/finetuning-output/"
ROLE_ARN = get_execution_role()  # You can change this to a specific role
ACCEPT_EULA = False  # Set to True to accept the base model's End-User License Agreement (OSS models only)
MODEL_PACKAGE_GROUP_NAME = ""  # Auto-generated based on use case

# Reward model — the Bedrock LLM used as judge
# Available models and regions: see references/rlaif_guide.md
REWARD_MODEL_ID = ""

# Builtin reward prompt value — choose one that matches your use case:
# "Builtin.Summarize", "Builtin.Faithfulness", "Builtin.ChainOfThought", "Builtin.Evaluation"
REWARD_PROMPT_VALUE = ""  

# Cell 3: Create Dataset and Model Package Group

# Create Model Package Group
try:
    model_package_group = ModelPackageGroup.create(
        model_package_group_name=MODEL_PACKAGE_GROUP_NAME,
        model_package_group_description="",
    )
    print(f"Created new model package group named {MODEL_PACKAGE_GROUP_NAME}")
except ClientError as e:
    if e.response['Error']['Code'] in ('ResourceInUse', 'ValidationException'):
        model_package_group = ModelPackageGroup.get(model_package_group_name=MODEL_PACKAGE_GROUP_NAME)
        print(f"There is already a model package group with the name {MODEL_PACKAGE_GROUP_NAME}.\nIf you want to save your finetuned model under a different name, change the value of MODEL_PACKAGE_GROUP_NAME in the previous cell.")
    else:
        raise

# Create Dataset
dataset = DataSet.create(
    name=MODEL_PACKAGE_GROUP_NAME,
    source=TRAINING_DATA_S3,
    wait=True
)
TRAINING_DATASET_ARN = dataset.arn

print(f"Here is your model package group ARN: {model_package_group.model_package_group_arn}\n")
print(f"Here is your training dataset ARN: {dataset.arn}")

# Cell 4: Configure Trainer

trainer = RLAIFTrainer(
    model=BASE_MODEL,
    model_package_group=model_package_group,
    reward_model_id=REWARD_MODEL_ID,
    reward_prompt=REWARD_PROMPT_VALUE,
    training_dataset=TRAINING_DATASET_ARN,
    s3_output_path=S3_OUTPUT_PATH,
    sagemaker_session=sagemaker_session,
    #accept_eula=ACCEPT_EULA,  # Uncomment for Meta models
    role=ROLE_ARN,
)

print("Here are the recommended hyperparameters for the current training job:")
print(f"Batch size:    {trainer.hyperparameters.global_batch_size}")
print(f"Learning rate: {trainer.hyperparameters.learning_rate}")
print(f"Epochs:        {trainer.hyperparameters.max_epochs}")

# Cell 5: Hyperparameter Overrides

# To change a hyperparameter, uncomment its corresponding line, and set the value you want.

# Note: If the value you choose is not supported for your model, you will get an error indicating the allowed range.

# Uncomment the following line to change the learning rate
# trainer.hyperparameters.learning_rate = 0.0002

# Uncomment the following line to change the batch size
# trainer.hyperparameters.global_batch_size = 16

# Uncomment the following line to change the number of epochs
# trainer.hyperparameters.max_epochs = 5

# Cell 6: Start Training

training_job = trainer.train(wait=True)

print(f"Training Job Name: {training_job.training_job_name}")
print(f"Training Status: {training_job.training_job_status}")

# Save manifest
manifest_dir = Path("[PROJECT_DIR]") / "manifests"
manifest_dir.mkdir(parents=True, exist_ok=True)
manifest_path = manifest_dir / f"training-{training_job.training_job_name}.json"
manifest_path.write_text(json.dumps({
    "training_job_name": training_job.training_job_name,
    "model_package_group_name": MODEL_PACKAGE_GROUP_NAME,
}, indent=2))
print(f"Manifest saved: {manifest_path}")

# Cell 7: Plot and Display Metrics  # NOTEBOOK_ONLY_SECTION

import matplotlib.pyplot as plt
import mlflow
from mlflow.tracking import MlflowClient

run_id = training_job.mlflow_details.mlflow_run_id
mlflow.set_tracking_uri(training_job.mlflow_config.mlflow_resource_arn)
client = MlflowClient()

metrics = [
    "critic/rewards/mean",
    "response_length/mean",
    "actor/entropy_loss",
    "actor/grad_norm",
    "critic/advantages/mean",
]

fig, axes = plt.subplots(1, len(metrics), figsize=(4 * len(metrics), 3))
for idx, metric in enumerate(metrics):
    history = client.get_metric_history(run_id, metric)
    if history:
        axes[idx].plot([h.step for h in history], [h.value for h in history], linewidth=2, marker='o', markersize=4)
        axes[idx].set_xlabel('Step')
        axes[idx].set_ylabel(metric.split('/')[-1])
        axes[idx].set_title(metric, fontweight='bold')
        axes[idx].grid(True, alpha=0.3)

plt.suptitle(f'Training Metrics: {training_job.training_job_name}', fontweight='bold')
plt.tight_layout()
plt.show()

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

Security

What our scanner noticed· Low risk

  • Instructions that use the network
  • Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
AWS Labs
Publisher
AWS Labs (Official)
Source
awslabs/agent-plugins · plugins/sagemaker-ai/skills/finetuning · commit fbefb37
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • NOTICE (added by AutoGineer from NOTICE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by AWS Labs or AWS Labs.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download finetuning.zip