Главная
Study mode:
on
1
Fine-tuning on a custom dataset
2
Video Overview
3
GPTs as statistical models
4
What is the reversal curse?
5
Synthetic dataset generation
6
Choosing the best batch size
7
What learning rate to use for fine-tuning?
8
How many epochs to train for?
9
Choosing the right base model
10
Step by step dataset generation
11
Fine-tuning script, step-by-step
12
Performance Ablation: Hyperparameters
13
Performance Ablation: Base Models
14
Final Recommendations for Fine-tuning for Memorization
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Dive deep into the intricacies of fine-tuning Large Language Models (LLMs) with a comprehensive 47-minute video tutorial. Explore key concepts such as GPTs as statistical models, the reversal curse, and synthetic dataset generation. Learn practical skills including selecting optimal batch sizes, determining appropriate learning rates, and choosing the right number of training epochs. Follow along with step-by-step instructions for dataset generation and fine-tuning script implementation. Analyze performance through hyperparameter ablation studies and base model comparisons. Conclude with valuable recommendations for fine-tuning LLMs specifically for memorization tasks, equipping you with the knowledge to enhance model performance in your own projects.

Fine-tuning LLMs - Every Step Explained for Memorization Tasks

Trelis Research
Add to list