Axolotl Universal Fine-tuning

YAML-driven LLM fine-tuning with Axolotl on Clore.ai — LoRA, QLoRA, DPO, multi-GPU

Axolotl wraps HuggingFace Transformers, PEFT, TRL, and DeepSpeed into a single YAML-driven interface. You define your model, dataset, training method, and hyperparameters in one config file — then launch with a single command. No Python scripting required for standard workflows.

All examples run on GPU servers rented through the CLORE.AI Marketplace.

Key Features

• YAML-only configuration — define everything in one file, no Python needed

• All training methods — LoRA, QLoRA, full fine-tune, DPO, ORPO, KTO, RLHF

• Multi-GPU out of the box — DeepSpeed ZeRO 1/2/3 and FSDP with one flag

• Sample packing — concatenate short examples to fill sequence length, 3–5× throughput gain

• Flash Attention 2 — automatic VRAM savings on supported hardware

• Broad model support — Llama 3.x, Mistral, Qwen 2.5, Gemma 2, Phi-4, DeepSeek, Falcon

• Built-in dataset formats — alpaca, sharegpt, chat_template, completion, and custom

Requirements

Component	Minimum	Recommended
GPU	RTX 3060 12 GB	RTX 4090 24 GB (×2+)
VRAM	12 GB	24+ GB
RAM	16 GB	64 GB
Disk	50 GB	100 GB
CUDA	11.8	12.1+
Python	3.10	3.11

Clore.ai pricing: RTX 4090 ≈ $0.5–2/day · RTX 3090 ≈ $0.3–1/day · RTX 3060 ≈ $0.15–0.3/day

Quick Start

1. Install Axolotl

# Clone and install
git clone https://github.com/OpenAccess-AI-Collective/axolotl.git
cd axolotl

pip install packaging ninja
pip install -e '.[flash-attn,deepspeed]'

Or use the Docker image (recommended for reproducibility):

docker run --gpus all -it --rm \
  -v /workspace:/workspace \
  winglian/axolotl:main-latest

2. Create a Config File

Save this as config.yml:

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_4bit: true
adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true

datasets:
  - path: yahma/alpaca-cleaned
    type: alpaca

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

wandb_project: axolotl-clore
wandb_name: llama3-qlora

output_dir: /workspace/axolotl-output

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
learning_rate: 2e-4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
warmup_steps: 10

bf16: auto
flash_attention: true
gradient_checkpointing: true

logging_steps: 10
save_strategy: steps
save_steps: 500
eval_steps: 500

evals_per_epoch:
val_set_size: 0.02

3. Launch Training

# Single GPU
accelerate launch -m axolotl.cli.train config.yml

# Multi-GPU (all available GPUs)
accelerate launch --multi_gpu -m axolotl.cli.train config.yml

Training progress logs to stdout and optionally to Weights & Biases.

Configuration Deep Dive

Dataset Formats

Axolotl supports multiple input formats natively:

# Alpaca-style (instruction / input / output)
datasets:
  - path: yahma/alpaca-cleaned
    type: alpaca

# ShareGPT multi-turn chat
datasets:
  - path: anon8231489123/ShareGPT_Vicuna_unfiltered
    type: sharegpt
    conversation: chatml

# Chat template (auto-detect from tokenizer)
datasets:
  - path: HuggingFaceH4/ultrachat_200k
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content

# Local JSONL file
datasets:
  - path: /workspace/data/my_dataset.jsonl
    type: alpaca
    ds_type: json

Multi-GPU with DeepSpeed

Create deepspeed_zero2.json:

{
  "bf16": { "enabled": true },
  "zero_optimization": {
    "stage": 2,
    "offload_optimizer": { "device": "cpu" },
    "allgather_partitions": true,
    "allgather_bucket_size": 5e8,
    "reduce_scatter": true,
    "reduce_bucket_size": 5e8,
    "overlap_comm": true,
    "contiguous_gradients": true
  },
  "train_micro_batch_size_per_gpu": "auto",
  "gradient_accumulation_steps": "auto",
  "gradient_clipping": 1.0
}

Add to your config:

deepspeed: deepspeed_zero2.json

Then launch:

accelerate launch --num_processes 4 -m axolotl.cli.train config.yml

DPO / ORPO Alignment

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
rl: dpo
# or: rl: orpo

datasets:
  - path: argilla/ultrafeedback-binarized-preferences
    type: chat_template.default
    field_messages: chosen
    field_chosen: chosen
    field_rejected: rejected

dpo_beta: 0.1

Full Fine-Tune (No LoRA)

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct

# No adapter, no quantization
adapter:
load_in_4bit: false
load_in_8bit: false

learning_rate: 5e-6
micro_batch_size: 1
gradient_accumulation_steps: 8
gradient_checkpointing: true
flash_attention: true
bf16: auto

deepspeed: deepspeed_zero3.json  # required for 8B+ full fine-tune

Usage Examples

Inference After Training

# Launch interactive inference
accelerate launch -m axolotl.cli.inference config.yml \
  --lora_model_dir /workspace/axolotl-output

Merge LoRA into Base Model

accelerate launch -m axolotl.cli.merge_lora config.yml \
  --lora_model_dir /workspace/axolotl-output \
  --output_dir /workspace/merged-model

Preprocess Dataset (Validate Before Training)

python -m axolotl.cli.preprocess config.yml

This tokenizes and validates the dataset. Useful for catching format errors before a long training run.

VRAM Usage Reference

Model	Method	GPUs	VRAM/GPU	Config
Llama 3.1 8B	QLoRA 4bit	1	~12 GB	r=32, seq_len=2048
Llama 3.1 8B	LoRA 16bit	1	~20 GB	r=16, seq_len=2048
Llama 3.1 8B	Full	2	~22 GB	DeepSpeed ZeRO-3
Qwen 2.5 14B	QLoRA 4bit	1	~16 GB	r=16, seq_len=2048
Llama 3.3 70B	QLoRA 4bit	2	~22 GB	r=16, seq_len=2048
Llama 3.3 70B	Full	4	~40 GB	DeepSpeed ZeRO-3+offload

Tips

• Always enable sample_packing: true — single biggest throughput improvement (3–5× on short datasets)

• Use flash_attention: true on Ampere+ GPUs for 20–40% VRAM savings

• Start with QLoRA for experiments, switch to full fine-tune only when LoRA quality plateaus

• Set val_set_size: 0.02 to monitor overfitting during training

• Preprocess first — run axolotl.cli.preprocess to validate data formatting before committing to a long run

• Use the Docker image for reproducible environments — avoids dependency conflicts

• lora_target_linear: true applies LoRA to all linear layers, generally better than targeting only attention

Troubleshooting

Problem	Solution
OutOfMemoryError	Lower micro_batch_size to 1, enable gradient_checkpointing
Dataset format errors	Run python -m axolotl.cli.preprocess config.yml to debug
sample_packing slow on first epoch	Normal — initial packing computation is one-time
Multi-GPU training hangs	Check NCCL: export NCCL_DEBUG=INFO, ensure all GPUs visible
flash_attention import error	Install: pip install flash-attn --no-build-isolation
Loss not decreasing	Lower LR to 1e-4, increase warmup, check dataset quality
WandB connection error	Run wandb login or set wandb_project: to empty string

Resources

• Axolotl GitHub

• Example Configs

• CLORE.AI Marketplace