SimPO 训练 — 用于 LLM 对齐的简单偏好优化

{/* 此页面由 website/scripts/generate-skill-docs.py 从技能的 SKILL.md 自动生成。请编辑源文件 SKILL.md，而非此页面。 */}

Simpo Training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

技能元数据

来源	可选 — 通过 hermes skills install official/mlops/simpo
路径	optional-skills/mlops/simpo
版本	1.0.0
作者	Orchestra Research
许可证	MIT
依赖项	torch, transformers, datasets, trl, accelerate
平台	linux, macos, windows
标签	Post-Training, SimPO, Preference Optimization, Alignment, DPO Alternative, Reference-Free, LLM Alignment, Efficient Training

参考：完整 SKILL.md

:::info 以下是 Hermes 在触发此技能时加载的完整技能定义。这是技能激活时代理所看到的指令。 :::

SimPO - Simple Preference Optimization

快速开始

SimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model.

Installation:

# Create environment
conda create -n simpo python=3.10 && conda activate simpo
 
# Install PyTorch 2.2.2
# Visit: https://pytorch.org/get-started/locally/
 
# Install alignment-handbook
git clone https://github.com/huggingface/alignment-handbook.git
cd alignment-handbook
python -m pip install .
 
# Install Flash Attention 2
python -m pip install flash-attn --no-build-isolation

Training (Mistral 7B):

ACCELERATE_LOG_LEVEL=info accelerate launch \
  --config_file accelerate_configs/deepspeed_zero3.yaml \
  scripts/run_simpo.py \
  training_configs/mistral-7b-base-simpo.yaml

常见工作流程

Workflow 1: Train from base model (Mistral 7B)

Config (mistral-7b-base-simpo.yaml):

# Model
model_name_or_path: mistralai/Mistral-7B-v0.1
torch_dtype: bfloat16
 
# Dataset
dataset_mixer:
  HuggingFaceH4/ultrafeedback_binarized: 1.0
dataset_splits:
  - train_prefs
  - test_prefs
 
# SimPO hyperparameters
beta: 2.0                  # Reward scaling (2.0-10.0)
gamma_beta_ratio: 0.5       # Target margin (0-1)
loss_type: sigmoid          # sigmoid or hinge
sft_weight: 0.0             # Optional SFT regularization
 
# Training
learning_rate: 5e-7         # Critical: 3e-7 to 1e-6
num_train_epochs: 1
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
 
# Output
output_dir: ./outputs/mistral-7b-simpo

Launch training:

accelerate launch --config_file accelerate_configs/deepspeed_zero3.yaml \
  scripts/run_simpo.py training_configs/mistral-7b-base-simpo.yaml

Workflow 2: Fine-tune instruct model (Llama 3 8B)

Config (llama3-8b-instruct-simpo.yaml):

model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 
dataset_mixer:
  argilla/ultrafeedback-binarized-preferences-cleaned: 1.0
 
beta: 2.5
gamma_beta_ratio: 0.5
learning_rate: 5e-7
sft_weight: 0.1             # Add SFT loss to preserve capabilities
 
num_train_epochs: 1
per_device_train_batch_size: 2
gradient_accumulation_steps: 4
output_dir: ./outputs/llama3-8b-simpo

Launch:

accelerate launch --config_file accelerate_configs/deepspeed_zero3.yaml \
  scripts/run_simpo.py training_configs/llama3-8b-instruct-simpo.yaml

Workflow 3: Reasoning-intensive tasks (lower LR)

For math/code tasks:

model_name_or_path: deepseek-ai/deepseek-math-7b-base
 
dataset_mixer:
  argilla/distilabel-math-preference-dpo: 1.0
 
beta: 5.0                   # Higher for stronger signal
gamma_beta_ratio: 0.7       # Larger margin
learning_rate: 3e-7         # Lower LR for reasoning
sft_weight: 0.0
 
num_train_epochs: 1
per_device_train_batch_size: 1
gradient_accumulation_steps: 16

何时使用 vs alternatives

使用 SimPO 的情况：

• Want simpler training than DPO (no reference model)
• Have preference data (chosen/rejected pairs)
• Need better performance than DPO
• Limited compute resources
• Single-node training sufficient

Algorithm selection:

• SimPO: Simplest, best performance, no reference model
• DPO: Need reference model baseline, more conservative
• PPO: Maximum control, need reward model, complex setup
• GRPO: Memory-efficient RL, no critic

Use alternatives instead:

• OpenRLHF: Multi-node distributed training, PPO/GRPO
• TRL: Need multiple methods in one framework
• DPO: Established baseline comparison

常见问题

问题：Loss divergence

Reduce learning rate:

learning_rate: 3e-7  # Reduce from 5e-7

Reduce beta:

beta: 1.0  # Reduce from 2.0

问题：Model forgets capabilities

Add SFT regularization:

sft_weight: 0.1  # Add SFT loss component

问题：Poor preference separation

Increase beta and margin:

beta: 5.0            # Increase from 2.0
gamma_beta_ratio: 0.8  # Increase from 0.5

问题：OOM during training

Reduce batch size:

per_device_train_batch_size: 1
gradient_accumulation_steps: 16  # Maintain effective batch

Enable gradient checkpointing:

gradient_checkpointing: true

高级主题

Loss functions: See references/loss-functions.md for sigmoid vs hinge loss, mathematical formulations, and when to use each.

Hyperparameter tuning: See references/hyperparameters.md for beta, gamma, learning rate selection guide, and model-size-specific recommendations.

Dataset preparation: See references/datasets.md for preference data formats, quality filtering, and custom dataset creation.

硬件要求

• GPU: NVIDIA A100/H100 recommended
• VRAM:
  • 7B model: 1× A100 40GB (DeepSpeed ZeRO-3)
  • 8B model: 2× A100 40GB
  • 70B model: 8× A100 80GB
• Single-node: DeepSpeed ZeRO-3 sufficient
• Mixed precision: BF16 recommended

内存优化：

• DeepSpeed ZeRO-3 (default config)
• Gradient checkpointing
• Flash Attention 2

资源

• Paper: https://arxiv.org/abs/2405.14734 (NeurIPS 2024)
• GitHub: https://github.com/princeton-nlp/SimPO
• Models: https://huggingface.co/princeton-nlp
• Alignment Handbook: https://github.com/huggingface/alignment-handbook