A team of developers starts with a large, general-purpose language model that was trained on a vast corpus of internet text. Their goal is to create a specialized tool that can classify legal documents into specific categories (e.g., 'contract', 'litigation', 'intellectual property'). To do this, they add a new classification component to the model and then train the entire system on a curated, labeled dataset of legal documents. Which statement best analyzes the state of the model's parameters after this training process is successfully completed?
0
1
Tags
Data Science
Ch.1 Pre-training - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Ch.2 Generative Models - Foundations of Large Language Models
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Inference Process with a Fine-Tuned Model
Fine-Tuning Objective Function
Complexity and Factors of BERT Fine-Tuning
Formula for Integrating a Prediction Network with a Pre-trained BERT Model
A team of developers starts with a large, general-purpose language model that was trained on a vast corpus of internet text. Their goal is to create a specialized tool that can classify legal documents into specific categories (e.g., 'contract', 'litigation', 'intellectual property'). To do this, they add a new classification component to the model and then train the entire system on a curated, labeled dataset of legal documents. Which statement best analyzes the state of the model's parameters after this training process is successfully completed?
Diagnosing a Fine-Tuning Failure
A machine learning engineer wants to adapt a large, general-purpose language model to perform sentiment analysis on customer reviews. Arrange the following steps in the correct chronological order to successfully specialize the model for this new task.