The best way for busy people to learn what they've always wanted to. Personalized courses, paced for your week, written one lesson at a time.
Engineering · Personalized course
Module 01
Foundations and pretraining
Module 02
Fine-tuning for real tasks
Learnable prepares a course syllabus to help you achieve your learning goals. Approve it as-is or iterate with your assistant.
How familiar are you with machine learning?
Pick one
What do you want to walk away able to do?
Select all that apply
What hardware will you have?
Pick one
Module 02
Fine-tuning for real tasks
Lessons get the format the subject calls for. A theory chapter is a careful read. A coding lesson is a runnable sandbox. An intuition lesson hands you an interactive UI to play around with.
Training LLMs · Module 1, Lesson 2
When a language model “reads” a sentence, it never sees words. It sees tokens — small, tokenizer-specific chunks of text that may or may not align with word boundaries.
Each token maps to a vector called an embedding. Two tokens with similar meanings end up close together in embedding space, which is half the reason this works at all.
Question 1 of 4
Your LoRA fine-tune is running. Which loss curve says it's actually learning?
Correct
A clean drop-then-plateau is the canonical “learning is happening” shape. Flat loss means nothing's flowing; spiking loss usually means your learning rate is too high.
# LoRA fine-tune on a small base
from peft import get_peft_model, LoraConfig
from transformers import AutoModel
base = AutoModel.from_pretrained(
"Qwen/Qwen2.5-0.5B",
)
config = LoraConfig(r=8, lora_alpha=16)
model = get_peft_model(base, config)
model.print_trainable_parameters()Hyperparameter playground
How much LoRA rank do you want?
Every lesson you finish builds towards your learning goals and gives you exciting progress to look back on.