Fine-tuning con PPO

Dopo aver inizializzato il trainer, ora devi impostare il loop per effettuare il fine-tuning del modello.

Il reward trainer ppo_trainer è stato inizializzato usando la classe PPOTrainer dalla libreria Python trl.

Questo esercizio fa parte del corso

Reinforcement Learning from Human Feedback (RLHF)

Visualizza il corso

Istruzioni dell'esercizio

Genera tensori di risposta usando gli input ids e il trainer all'interno del loop PPO.
Completa lo step nel loop PPO che usa query, risposte e dati di ricompensa per ottimizzare il modello PPO.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

for batch in tqdm(ppo_trainer.dataloader): 

    # Generate responses for the given queries using the trainer
    response_tensors = ____(batch["input_ids"])

    batch["response"] = [tokenizer.decode(r.squeeze()) for r in response_tensors]

    texts = [q + r for q, r in zip(batch["query"], batch["response"])]

    rewards = reward_model(texts)

    # Training PPO step with the query, responses ids, and rewards
    stats = ____(batch["input_ids"], response_tensors, rewards)

    ppo_trainer.log_stats(stats, batch, rewards)

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Reinforcement Learning from Human Feedback (RLHF)

AvançadoNível de habilidade

4.8+

Inizia il corso gratis

This chapter introduces the basics of Reinforcement Learning with Human Feedback (RLHF), a technique that uses human input to help AI models learn more effectively. Get started with RLHF by understanding how it differs from traditional reinforcement learning and why human feedback can enhance AI performance in various domains.

Exercise 1: Introduction to RLHF Exercise 2: Text generation with RLHF Exercise 3: Classifying generated text for RLHF Exercise 4: RL vs. RLHF Exercise 5: Exploring pre-trained LLMs Exercise 6: Tokenize a text dataset Exercise 7: Fine-tuning for review classification Exercise 8: Preparing data for RLHF Exercise 9: Preparing the preference dataset Exercise 10: Extracting prompts

Discover how to set up systems for gathering human feedback in this Chapter. Learn best practices for collecting high-quality data, from pairwise comparisons to uncertainty sampling, and explore strategies for enhancing your data collection.

Exercise 1: Methods for high-quality feedback gathering Exercise 2: Understanding comparison and rating in RLHF Exercise 3: Comparing slogans for a gym campaign Exercise 4: Measuring feedback quality and relevance Exercise 5: Low confidence Exercise 6: K-means for feedback clustering Exercise 7: Active learning Exercise 8: Implementing an active learning pipeline Exercise 9: Active learning loop

In this Chapter, you'll get into the core of Reinforcement Learning from Human Feedback training. This includes exploring fine-tuning with PPO, techniques to train efficiently, and handling potential divergences from your metrics' objectives.

Exercise 1: Esplorare i modelli di ricompensa Exercise 2: Inizializzare il reward Exercise 3: Configurare il reward trainer Exercise 4: Training con PPO Exercise 5: Inizializza il trainer PPO Exercise 6: Fine-tuning con PPO

Esercizio in corso

Exercise 7: Ottimizzazione efficiente del fine-tuning in RLHF Exercise 8: Preparazione al training a 8 bit Exercise 9: Addestra con LoRA

Explore key techniques for assessing and improving model performance in this last Chapter of Reinforcement Learning from Human Feedback (RLHF): from fine-tuning metrics to incorporating diverse feedback sources, you'll be provided with a comprehensive toolkit to refine your models effectively.

Exercise 1: Model metrics and adjustments Exercise 2: Mitigating negative KL divergence Exercise 3: Checking the reward model Exercise 4: Incorporating diverse feedback sources Exercise 5: Majority voting on multiple data sources Exercise 6: Unreliable data source identification Exercise 7: Evaluating RLHF models Exercise 8: Interpreting curves Exercise 9: Evaluating RLHF with metrics Exercise 10: Wrapping up your RLHF journey