Penyetelan halus dengan PPO

Setelah menginisialisasi trainer, sekarang Anda perlu menyiapkan loop untuk menyetel halus model.

Reward trainer ppo_trainer telah diinisialisasi menggunakan kelas PPOTrainer dari pustaka Python trl.

Latihan ini adalah bagian dari kursus

Reinforcement Learning from Human Feedback (RLHF)

Petunjuk latihan

Hasilkan tensor respons menggunakan input ids, dan trainer di dalam loop PPO.
Lengkapi langkah di dalam loop PPO yang menggunakan kueri, respons, dan data reward untuk mengoptimalkan model PPO.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

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)

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Reinforcement Learning from Human Feedback (RLHF)

SkillTag.level.advancedSkillTag.label

4.8+

Mulai Kursus 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: Menjelajahi reward model Exercise 2: Menginisialisasi reward Exercise 3: Menyiapkan reward trainer Exercise 4: Pelatihan dengan PPO Exercise 5: Inisialisasi pelatih PPO Exercise 6: Penyetelan halus dengan PPO

Latihan Saat Ini

Exercise 7: Fine-tuning yang efisien dalam RLHF Exercise 8: Siapkan untuk Pelatihan 8-bit Exercise 9: Latih dengan 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