trl-training

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:

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:

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:

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