Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
Installs just this skill. Get the whole plugin for auto-invocation.
⚡ How it fires
How this skill gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/trl-training
👁️ Context preview
The summary Claude sees to decide when to auto-load this skill.
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
📊 Stats
Stars10,858
Forks722
LanguagePython
LicenseApache-2.0
📦 Ships with huggingface-skills
</> SKILL.md
trl-training.SKILL.md
---name: trl-training
description: Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
license: Apache-2.0
metadata:
version: "1.0.0"
author: huggingface
commands:
- trl sft
- trl dpo
- trl grpo
- trl kto
- trl rloo
- trl reward
categories:
- machine-learning
- llm-training
- reinforcement-learning
tags:
- rlhf
- supervised-fine-tuning
- dpo
- grpo
- huggingface
- transformers
documentation: https://huggingface.co/docs/trl/en/clis
---# TRL Training Skill
You are an expert at using the TRL (Transformers Reinforcement Learning) library to train and fine-tune large language models.
## Overview
TRL provides CLI commands for post-training foundation models using state-of-the-art techniques:
- **SFT** (Supervised Fine-Tuning): Fine-tune models on instruction-following or conversational datasets
- **DPO** (Direct Preference Optimization): Align models using preference data
- **GRPO** (Group Relative Policy Optimization): Train models by ranking multiple sampled outputs relative to each other and optimizing based on their comparative rewards.
- **RLOO** (Reinforce Leave One Out): Online RL training with generation-based rewards
- **Reward Model Training**: Train reward models for RLHF
TRL is built on top of Hugging Face Transformers and Accelerate, providing seamless integration with the Hugging Face ecosystem.
## Core Commands
### trl sft - Supervised Fine-Tuning
Fine-tune language models on instruction-following or conversational datasets.
**Full training:**
```bash
trl sft \
--model_name_or_path Qwen/Qwen2-0.5B \
--dataset_name trl-lib/Capybara \
--learning_rate 2.0e-5 \
--num_train_epochs 1 \
--packing \
--per_device_train_batch_size 2 \
--gradient_accumulation_steps 8 \
--eos_token '<|im_end|>' \
--eval_strategy steps \
--eval_steps 100 \
--output_dir Qwen2-0.5B-SFT \
--push_to_hub
```
**Train with LoRA adapters:**
```bash
trl sft \
--model_name_or_path Qwen/Qwen2-0.5B \
--dataset_name trl-lib/Capybara \
--learning_rate 2.0e-4 \
--num_train_epochs 1 \
--packing \
--per_device_train_batch_size 2 \
--gradient_accumulation_steps 8 \
--eos_token '<|im_end|>' \
--eval_strategy steps \
--eval_steps 100 \
--use_peft \
--lora_r 32 \
--lora_alpha 16 \
--output_dir Qwen2-0.5B-SFT \
--push_to_hub
```
### trl dpo - Direct Preference Optimization
Align models using preference data (chosen/rejected pairs).
**Full training:**
```bash
trl dpo \
--dataset_name trl-lib/ultrafeedback_binarized \
--model_name_or_path Qwen/Qwen2-0.5B-Instruct \
--learning_rate 5.0e-7 \
--num_train_epochs 1 \
--per_device_train_batch_size 2 \
--max_steps 1000 \
--gradient_accumulation_steps 8 \
--eval_strategy steps \
--eval_steps 50 \
--output_dir Qwen2-0.5B-DPO \
--no_remove_unused_columns
```
**Train with LoRA adapters:**
```bash
trl dpo \
--dataset_name trl-lib/ultrafeedback_binarized \
--model_name_or_path Qwen/Qwen2-0.5B-Instruct \
--learning_rate 5.0e-6 \
--num_train_epochs 1 \
--per_device_train_batch_size 2 \
--max_steps 1000 \
--gradient_accumulation_steps 8 \
--eval_strategy steps \
--eval_steps 50 \
--output_dir Qwen2-0.5B-DPO \
--no_remove_unused_columns \
--use_peft \
--lora_r 32 \
--lora_alpha 16
```
### trl grpo - Group Relative Policy Optimization
Train models using reward functions or LLM-as-a-judge for evaluating generations and providing rewards.
**Basic usage:**
```bash
trl grpo \
--model_name_or_path Qwen/Qwen2.5-0.5B \
--dataset_name trl-lib/gsm8k \
--reward_funcs accuracy_reward \
--output_dir Qwen2-0.5B-GRPO \
--push_to_hub
```
### trl rloo - Reinforce Leave One Out
Online RL training where the model generates text and receives rewards based on custom criteria.
