Education & Training
EVALS.md · 21 documents
Domain 5: Testing, Validation, and Troubleshooting
**AIP-C01 Study Guide — Dr. Priya Ramanathan**
Training Readiness Checklist
Before launching a large-scale training or tuning run, verify the following gates are closed.
Lesson 01: Evaluation Frameworks Overview
**Module 07: Evaluation and Testing**
LLM Evaluation — Interview Grill
> 70+ active-recall questions. Pair with `LLM_EVALUATION_DEEP_DIVE.md`.
prompt-eval-designer
name: prompt-eval-designer
AICL Public Review Guide
This guide is for developers, researchers, AI-system builders, and model users reviewing AICL for the first time.
Training FAQ
When performing classical supervised fine-tuning of language models, the loss (especially the validation loss) serves as a good indicator of the training progress. However, in Reinforcement Learning (RL), the loss becomes less informative about the model's performance, and its value may fluctuate while the actual performance improves.
Questions and Answers to Supervised Learning.
5. What are the advantages and disadvantages of supervised learning compared to unsupervised and semi-supervised learning?
Structuring Machine Learning Project
_Notes from this section are adpated from Andrew Ng's DL specialization course 3 + Andrew's Machine Learning Yearning Book_, many of the notes here are copied verbatim, all rights belong to Andrew Ng.
End-of-term exam
- Each student will be randomly assigned 2 topics, one about NLP and one about Python.
Motivating Principles
This project was created to serve as a resource for newcomers and developers, and also from
Introduction
- [Introduction](#introduction)
🤔 What is this?
Translations: [EN(you are here)](EN.md), [RU](README.md)
🚀 Ultra-Advanced Features - FWG Training Guide
**Next-Generation Interactive Learning Platform**
Code Challenge 4 Sanitized Rubric
The student is able to:
proj1rubric
| Notes|Self Assessment zero (none), one (a litte), two (somewhat), three (a lot)| Evidence|
pyttb User Guide and Rubric
The pyttb package is a powerful toolset for working with tensors in Python, designed to cater to a wide range of users, from beginners to advanced. This user guide and rubric will assist new users in understanding the capabilities of the pyttb package and how it can meet their specific needs.
Presentation Evaluator — Prototype Plan
A post-hoc analysis system that evaluates academic student presentations (~10 min) from recorded video. The system processes a single front-facing camera recording, extracts speech and body language metrics, and produces a descriptive report benchmarked against TED talk norms.
MLOps Learning Path (GCP Focused - Solid, Comprehensive & Practical)
**Goal:** Become job-ready for an MLOps role focusing on GCP, leveraging backend/fullstack/DevOps experience. Build deep, practical MLOps skills by blending core concepts with immediate, focused hands-on application using reliable resources. Understand both GCP's managed services and underlying open-source foundations like Kubeflow. Forget rigid timelines; focus on mastering each stage.
LAB3-INSTRUCTIONS
* [Background](LAB3-INSTRUCTIONS.md#background)
Work in progress: Batched LLM inference
Note: This notebook is a work in progress.