Scaling PyTorch Model Training With Minimal Code Changes

Sebastian Raschka · Beginner ·🧠 Large Language Models ·2y ago
Sebastian's books: https://sebastianraschka.com/books/ Code examples: https://github.com/rasbt/cvpr2023 In this short tutorial, I will show you how to accelerate the training of LLMs and Vision Transformers with minimal code changes using open-source libraries. --- To support this channel, please consider purchasing a copy of my books: https://sebastianraschka.com/books/ --- https://x.com/rasbt https://linkedin.com/in/sebastianraschka/ https://magazine.sebastianraschka.com
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Sebastian Raschka · Sebastian Raschka · 0 of 60

← Previous Next →
1 Intro to Deep Learning -- L06.5 Cloud Computing [Stat453, SS20]
Intro to Deep Learning -- L06.5 Cloud Computing [Stat453, SS20]
Sebastian Raschka
 2 Intro to Deep Learning -- L09 Regularization [Stat453, SS20]
Intro to Deep Learning -- L09 Regularization [Stat453, SS20]
Sebastian Raschka
 3 Intro to Deep Learning -- L10 Input and Weight Normalization Part 1/2 [Stat453, SS20]
Intro to Deep Learning -- L10 Input and Weight Normalization Part 1/2 [Stat453, SS20]
Sebastian Raschka
 4 Intro to Deep Learning -- L10 Input and Weight Normalization Part 2/2 [Stat453, SS20]
Intro to Deep Learning -- L10 Input and Weight Normalization Part 2/2 [Stat453, SS20]
Sebastian Raschka
 5 Intro to Deep Learning -- L11 Common Optimization Algorithms [Stat453, SS20]
Intro to Deep Learning -- L11 Common Optimization Algorithms [Stat453, SS20]
Sebastian Raschka
 6 Intro to Deep Learning -- L12 Intro to Convolutional Neural Networks (Part 1) [Stat453, SS20]
Intro to Deep Learning -- L12 Intro to Convolutional Neural Networks (Part 1) [Stat453, SS20]
Sebastian Raschka
 7 Intro to Deep Learning -- L13 Intro to Convolutional Neural Networks (Part 2) 1/2 [Stat453, SS20]
Intro to Deep Learning -- L13 Intro to Convolutional Neural Networks (Part 2) 1/2 [Stat453, SS20]
Sebastian Raschka
 8 Intro to Deep Learning -- L13 Intro to Convolutional Neural Networks (Part 2) 2/2 [Stat453, SS20]
Intro to Deep Learning -- L13 Intro to Convolutional Neural Networks (Part 2) 2/2 [Stat453, SS20]
Sebastian Raschka
 9 Intro to Deep Learning -- L14 Intro to Recurrent Neural Networks [Stat453, SS20]
Intro to Deep Learning -- L14 Intro to Recurrent Neural Networks [Stat453, SS20]
Sebastian Raschka
 10 Intro to Deep Learning -- L15 Autoencoders [Stat453, SS20]
Intro to Deep Learning -- L15 Autoencoders [Stat453, SS20]
Sebastian Raschka
 11 Intro to Deep Learning -- L16 Generative Adversarial Networks [Stat453, SS20]
Intro to Deep Learning -- L16 Generative Adversarial Networks [Stat453, SS20]
Sebastian Raschka
 12 Intro to Deep Learning -- Student Presentations, Day 1 [Stat453, SS20]
Intro to Deep Learning -- Student Presentations, Day 1 [Stat453, SS20]
Sebastian Raschka
 13 1.2 What is Machine Learning (L01: What is Machine Learning)
1.2 What is Machine Learning (L01: What is Machine Learning)
Sebastian Raschka
 14 1.3 Categories of Machine Learning (L01: What is Machine Learning)
1.3 Categories of Machine Learning (L01: What is Machine Learning)
Sebastian Raschka
 15 1.4 Notation (L01: What is Machine Learning)
1.4 Notation (L01: What is Machine Learning)
Sebastian Raschka
 16 1.1 Course overview (L01: What is Machine Learning)
1.1 Course overview (L01: What is Machine Learning)
Sebastian Raschka
 17 1.5 ML application (L01: What is Machine Learning)
1.5 ML application (L01: What is Machine Learning)
Sebastian Raschka
 18 1.6 ML motivation (L01: What is Machine Learning)
1.6 ML motivation (L01: What is Machine Learning)
Sebastian Raschka
 19 2.1 Introduction to NN (L02: Nearest Neighbor Methods)
2.1 Introduction to NN (L02: Nearest Neighbor Methods)
Sebastian Raschka
 20 2.2 Nearest neighbor decision boundary (L02: Nearest Neighbor Methods)
2.2 Nearest neighbor decision boundary (L02: Nearest Neighbor Methods)
Sebastian Raschka
 21 2.3 K-nearest neighbors (L02: Nearest Neighbor Methods)
2.3 K-nearest neighbors (L02: Nearest Neighbor Methods)
Sebastian Raschka
 22 2.4 Big O of K-nearest neighbors (L02: Nearest Neighbor Methods)
2.4 Big O of K-nearest neighbors (L02: Nearest Neighbor Methods)
Sebastian Raschka
 23 2.5 Improving k-nearest neighbors (L02: Nearest Neighbor Methods)
2.5 Improving k-nearest neighbors (L02: Nearest Neighbor Methods)
Sebastian Raschka
 24 2.6 K-nearest neighbors in Python (L02: Nearest Neighbor Methods)
2.6 K-nearest neighbors in Python (L02: Nearest Neighbor Methods)
Sebastian Raschka
 25 3.1 (Optional) Python overview
3.1 (Optional) Python overview
Sebastian Raschka
 26 3.2 (Optional) Python setup
3.2 (Optional) Python setup
Sebastian Raschka
 27 3.3 (Optional) Running Python code
3.3 (Optional) Running Python code
Sebastian Raschka
 28 4.1 Intro to NumPy (L04: Scientific Computing in Python)
4.1 Intro to NumPy (L04: Scientific Computing in Python)
Sebastian Raschka
 29 4.2 NumPy Array Construction and Indexing (L04: Scientific Computing in Python)
4.2 NumPy Array Construction and Indexing (L04: Scientific Computing in Python)
Sebastian Raschka
 30 4.4 NumPy Broadcasting (L04: Scientific Computing in Python)
4.4 NumPy Broadcasting (L04: Scientific Computing in Python)
Sebastian Raschka
 31 4.5 NumPy Advanced Indexing -- Memory Views and Copies (L04: Scientific Computing in Python)
4.5 NumPy Advanced Indexing -- Memory Views and Copies (L04: Scientific Computing in Python)
Sebastian Raschka
 32 4.3 NumPy Array Math and Universal Functions (L04: Scientific Computing in Python)
4.3 NumPy Array Math and Universal Functions (L04: Scientific Computing in Python)
Sebastian Raschka
 33 4.7 Reshaping NumPy Arrays (L04: Scientific Computing in Python)
4.7 Reshaping NumPy Arrays (L04: Scientific Computing in Python)
Sebastian Raschka
 34 4.6 NumPy Random Number Generators (L04: Scientific Computing in Python)
4.6 NumPy Random Number Generators (L04: Scientific Computing in Python)
Sebastian Raschka
 35 4.8 NumPy Comparison Operators and Masks (L04: Scientific Computing in Python)
4.8 NumPy Comparison Operators and Masks (L04: Scientific Computing in Python)
Sebastian Raschka
 36 4.9 NumPy Linear Algebra Basics (L04: Scientific Computing in Python)
4.9 NumPy Linear Algebra Basics (L04: Scientific Computing in Python)
Sebastian Raschka
 37 4.10 Matplotlib (L04: Scientific Computing in Python)
4.10 Matplotlib (L04: Scientific Computing in Python)
Sebastian Raschka
 38 5.1 Reading a Dataset from a Tabular Text File (L05: Machine Learning with Scikit-Learn)
5.1 Reading a Dataset from a Tabular Text File (L05: Machine Learning with Scikit-Learn)
Sebastian Raschka
 39 5.2 Basic data handling (L05: Machine Learning with Scikit-Learn)
5.2 Basic data handling (L05: Machine Learning with Scikit-Learn)
Sebastian Raschka
 40 5.3 Object Oriented Programming & Python Classes (L05: Machine Learning with Scikit-Learn)
5.3 Object Oriented Programming & Python Classes (L05: Machine Learning with Scikit-Learn)
Sebastian Raschka
 41 5.4 Intro to Scikit-learn (L05: Machine Learning with Scikit-Learn)
5.4 Intro to Scikit-learn (L05: Machine Learning with Scikit-Learn)
Sebastian Raschka
 42 5.5 Scikit-learn Transformer API (L05: Machine Learning with Scikit-Learn)
5.5 Scikit-learn Transformer API (L05: Machine Learning with Scikit-Learn)
Sebastian Raschka
 43 5.6 Scikit-learn Pipelines (L05: Machine Learning with Scikit-Learn)
5.6 Scikit-learn Pipelines (L05: Machine Learning with Scikit-Learn)
Sebastian Raschka
 44 6.1 Intro to Decision Trees (L06: Decision Trees)
6.1 Intro to Decision Trees (L06: Decision Trees)
Sebastian Raschka
 45 6.2 Recursive algorithms & Big-O (L06: Decision Trees)
6.2 Recursive algorithms & Big-O (L06: Decision Trees)
Sebastian Raschka
 46 6.3 Types of decision trees (L06: Decision Trees)
6.3 Types of decision trees (L06: Decision Trees)
Sebastian Raschka
 47 6.5 Gini & Entropy versus misclassification error (L06: Decision Trees)
6.5 Gini & Entropy versus misclassification error (L06: Decision Trees)
Sebastian Raschka
 48 6.6 Improvements & dealing with overfitting (L06: Decision Trees)
6.6 Improvements & dealing with overfitting (L06: Decision Trees)
Sebastian Raschka
 49 6.7 Code Example Implementing Decision Trees in Scikit-Learn (L06: Decision Trees)
6.7 Code Example Implementing Decision Trees in Scikit-Learn (L06: Decision Trees)
Sebastian Raschka
 50 7.1 Intro to ensemble methods (L07: Ensemble Methods)
7.1 Intro to ensemble methods (L07: Ensemble Methods)
Sebastian Raschka
 51 7.2 Majority Voting (L07: Ensemble Methods)
7.2 Majority Voting (L07: Ensemble Methods)
Sebastian Raschka
 52 7.3 Bagging (L07: Ensemble Methods)
7.3 Bagging (L07: Ensemble Methods)
Sebastian Raschka
 53 7.4 Boosting and AdaBoost (L07: Ensemble Methods)
7.4 Boosting and AdaBoost (L07: Ensemble Methods)
Sebastian Raschka
 54 7.5 Gradient Boosting (L07: Ensemble Methods)
7.5 Gradient Boosting (L07: Ensemble Methods)
Sebastian Raschka
 55 7.6 Random Forests (L07: Ensemble Methods)
7.6 Random Forests (L07: Ensemble Methods)
Sebastian Raschka
 56 7.7 Stacking (L07: Ensemble Methods)
7.7 Stacking (L07: Ensemble Methods)
Sebastian Raschka
 57 8.1 Intro to overfitting and underfitting (L08: Model Evaluation Part 1)
8.1 Intro to overfitting and underfitting (L08: Model Evaluation Part 1)
Sebastian Raschka
 58 8.2 Intuition behind bias and variance (L08: Model Evaluation Part 1)
8.2 Intuition behind bias and variance (L08: Model Evaluation Part 1)
Sebastian Raschka
 59 8.3 Bias-Variance Decomposition of the Squared Error (L08: Model Evaluation Part 1)
8.3 Bias-Variance Decomposition of the Squared Error (L08: Model Evaluation Part 1)
Sebastian Raschka
 60 8.4 Bias and Variance vs Overfitting and Underfitting (L08: Model Evaluation Part 1)
8.4 Bias and Variance vs Overfitting and Underfitting (L08: Model Evaluation Part 1)
Sebastian Raschka

Related AI Lessons

⚡
Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results
Learn how to use LLM agents to reproduce social-science results from just a paper's methods description and original data, broadening the scope of agentic reproduction in social science research
ArXiv cs.AI
 ⚡
Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
Learn how Memanto's typed semantic memory and information-theoretic retrieval enable efficient memory management for long-horizon agents, improving their performance and scalability.
ArXiv cs.AI
 ⚡
When Does LLM Self-Correction Help? A Control-Theoretic Markov Diagnostic and Verify-First Intervention
Learn when LLM self-correction helps using a control-theoretic Markov diagnostic and verify-first intervention, and apply this knowledge to improve LLM systems
ArXiv cs.AI
 ⚡
Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
Learn to characterize hidden randomness in Large Language Models using Background Temperature, a crucial concept for understanding nondeterminism in LLMs
ArXiv cs.AI
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →