How LLMs Work
Book Labs
All labs
25 Book labs · Training

The five moves — the heartbeat of training

From Chapter 25 of Large Language Models from the Ground Up. Every training run — from a toy bigram to a frontier model — is the same short loop repeated: sample a batch, forward, zero the gradients, backward, step. The book names these "the five moves" (introduced in Chapter 23) and calls the repeating loop the heartbeat. Walk it once, then let it run and watch the loss fall.

Interactive

One lap of the loop = one training step

Step walks the highlight one move around the cycle; a full lap commits a training step and drops a point on the loss curve. Play runs the heartbeat on its own — the same 3,000-step run from notebook 09.

Move 1 / 5 — sample a batch

Draw 32 random context windows from the training text.

0step / 3000
4.177train loss
0laps run
step 0cross-entropy lossstep 3000

Dashed lines mark the 4.17 random-guessing baseline (ln 65) and the 2.45 bigram ceiling. The real run lands at train 1.38 / val 1.59 — the curve here is calibrated to notebook 09's printed losses.

What to notice

The loop never changes shape. As the book puts it, the heartbeat is "get_batch → forward (which returns the loss) → zero_grad → backward (autograd computes every gradient) → step (nudge all 824,897 knobs downhill)." Order matters: clear, compute, step — in that order, every time. Watch the loss crash from 4.17 (pure guessing among 65 characters) down through the 2.45 bigram ceiling and level off near 1.38. That plateau isn't the loop wearing out — it's the model reaching the limit of what this size and this data can learn. Same five moves run 3,000 times; that is the entire act of "training" a GPT.

← Back to all labs