Majority voting on multiple data sources

Your team is developing an AI model to automatically generate smartphone quality control (QC) reports. For this purpose, you've collected preference data from three different quality control sources - an "Automated Vision System," a "Human Inspector," and "Customer Feedback". They've each labeled paired text samples as 'chosen' and 'rejected.' Each pair has a unique 'id', and every entry showcases a preferred QC review.

quality_df is a combined DataFrame loaded using pandas. It contains data from the three different data sources. Additionally, the Counter class has been pre-imported from the collections module.

Diese Übung ist Teil des Kurses

Reinforcement Learning from Human Feedback (RLHF)

Anleitung zur Übung

Count the occurrences of each (chosen, rejected) pairs in the vote function.
Find the (chosen, rejected) pair with the highest vote count.

Interaktive Übung

Vervollständige den Beispielcode, um diese Übung erfolgreich abzuschließen.

def majority_vote(df):
  	# Count occurrences of each (chosen, rejected) pair
    votes = ____
    # Find the (chosen, rejected) pair with the highest vote count
    winner = ____
    return winner

final_preferences = quality_df.groupby(['id']).apply(majority_vote)

print(final_preferences)

Code bearbeiten und ausführen

Diese Übung ist Teil des Kurses

Reinforcement Learning from Human Feedback (RLHF)

Hohe SchwierigkeitSchwierigkeitsgrad

4.8+

Kurs kostenlos starten

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: 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

Aktuelle Übung

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