De voorkeursgegevensset voorbereiden

In deze oefening werk je met een gegevensset die menselijke feedback bevat in de vorm van "chosen" en "rejected" outputs. Jouw taak is om de prompts uit de kolom "chosen" te extraheren en de data voor te bereiden voor het trainen van een rewardmodel.

De functie load_dataset uit datasets is al geïmporteerd

Deze oefening maakt deel uit van de cursus

Reinforcement Learning from Human Feedback (RLHF)

Cursus bekijken

Oefeninstructies

Laad de gegevensset trl-internal-testing/hh-rlhf-helpful-base-trl-style van Hugging Face.
Schrijf een functie die de prompt uit het veld 'content' haalt, met de aanname dat de prompt op index 0 staat in de invoer van de functie.
Pas de functie die de prompt extraheert toe op de subset 'chosen' van de gegevensset.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Load the dataset
preference_data = ____

# Define a function to extract the prompt
def extract_prompt(text):
    ____
    return prompt

# Apply the function to the dataset 
preference_data_with_prompt = ____(
    lambda sample: {**sample, 'prompt': ____(sample['chosen'])}
)

sample = preference_data_with_prompt.select(range(1))
print(sample['prompt'])

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Reinforcement Learning from Human Feedback (RLHF)

SkillTag.level.advancedSkillTag.label

4.8+

Begin de cursus 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: Introductie tot RLHF Exercise 2: Tekstgeneratie met RLHF Exercise 3: Gegenereerde tekst classificeren voor RLHF Exercise 4: RL vs. RLHF Exercise 5: Voorgetrainde LLM's verkennen Exercise 6: Tokenizeer een tekstgegevensset Exercise 7: Fine-tunen voor reviewclassificatie Exercise 8: Data voorbereiden voor RLHF Exercise 9: De voorkeursgegevensset voorbereiden

Huidige oefening

Exercise 10: Prompts extraheren

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: Reward models explored Exercise 2: Initializing the reward Exercise 3: Setting up the reward trainer Exercise 4: Training with PPO Exercise 5: Initialize the PPO trainer Exercise 6: PPO fine-tuning Exercise 7: Efficient fine-tuning in RLHF Exercise 8: Prepare for 8-bit Training Exercise 9: Train with 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