AGENT SKILL

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.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 2.0k
Forks
233

01 前言 Front Matter

name
simpo-training
tags
[ "Post-Training", "SimPO", "Preference Optimization", "Alignment", "DPO Alternative", "Reference-Free", "LLM Alignment", "Efficient Training" ]
author
Orchestra Research
license
MIT
version
1.0.0
description
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.
dependencies
[ "torch", "transformers", "datasets", "trl", "accelerate" ]

02 资源文件 3

03 SKILL.md 正文

SimPO - Simple Preference Optimization

Quick start

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

Common workflows

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

When to use vs alternatives

Use SimPO when:

  • 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

Common issues

Issue: Loss divergence

Reduce learning rate:

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

Reduce beta:

beta: 1.0  # Reduce from 2.0

Issue: Model forgets capabilities

Add SFT regularization:

sft_weight: 0.1  # Add SFT loss component

Issue: Poor preference separation

Increase beta and margin:

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

Issue: 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

Advanced topics

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.

Hardware requirements

  • 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

Memory optimization:

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

Resources

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

neuropixels-analysis

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

notebooklm

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Skill与智能体开发
★ 2.0k