Quickstart

Quickstart#

Run a fine-tuning job locally using an AIM Fine-tuning container. The container includes the CLI, training recipes and the training engine framework, and accelerator software required to run the job.

This example uses an AIM fine-tuning container that has the aimfttk training engine installed to run a supervised fine-tuning (SFT) job on the Gemma 3 27B IT model with LoRA training.

Prerequisites#

You need:

  • A Linux host with ROCm and Docker installed.

  • Access to an AMD GPU through /dev/kfd and /dev/dri.

  • A model and JSONL training dataset stored on the host.

  • The AIM Fine-tuning container image, such as the amdenterpriseai/aimft-aimfttk image from DockerHub.

Prepare local inputs#

Use a directory layout like this example:

training-job/
├── inputs/
│   ├── model/
│   └── data/
│       └── train.jsonl
└── outputs/

The model directory and dataset are mounted read-only. The output directory is writable so checkpoints and runtime files remain on the host.

Format the dataset#

The SFT dataset must be a JSONL file with one conversation per line. Each conversation contains a messages array with role and content fields:

{"messages":[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is fine-tuning?"},{"role":"assistant","content":"Fine-tuning adapts a pretrained model to a specific task or domain."}]}
{"messages":[{"role":"user","content":"Name one benefit of fine-tuning."},{"role":"assistant","content":"It can improve performance on a target task using a focused dataset."}]}

Conversations should use the roles expected by the selected model’s chat template, typically system, user, and assistant.

You could use SiloAI/AMD-eAIrs-SFT-Demo-Data sft-formatted demo dataset for running initial quickstart tests.

Start the job#

From the training-job directory run the container

export AIMFT_IMAGE=amdenterpriseai/aimft-aimfttk:<YOUR_TAG>

mkdir -p outputs

docker run --rm \
  --device=/dev/kfd --device=/dev/dri \
  --ipc=host \
  --mount type=bind,src="$PWD/inputs/model",dst=/model,readonly \
  --mount type=bind,src="$PWD/inputs/data",dst=/data,readonly \
  --mount type=bind,src="$PWD/outputs",dst=/output \
  -e AIMFT_MODEL_PATH=/model \
  -e AIMFT_TRAIN_DATA_PATH=/data/<your_dataset>.jsonl \
  -e AIMFT_OUTPUT_PATH=/output \
  -e AIM_MODEL_ID=google/gemma-3-27b-it \
  -e AIMFT_USE_ADAPTER=true \
  "$AIMFT_IMAGE"

Training logs are printed in the terminal running Docker. To keep the container available for a later log command, omit --rm, assign a name with --name aimft-sft, and run:

docker logs -f aimft-sft

Find the results#

When training finishes, inspect the host outputs/ directory. It contains runtime metadata, the rendered engine configuration, checkpoints, and the final adapter or model. With adapter training enabled, the final adapter is written to outputs/checkpoint-final-adapter.

The standardized SFT image interface documents all supported mount paths and environment variables.

For Kubernetes execution, see Run standalone fine-tuning on Kubernetes.

Contents