training

The process of fitting a model'smodel, n.: A simplified working version of something. In AI it usually means the trained program, a big set of learned numbers, that takes an input and produces an answer, prediction or piece of content. parametersparameter, n.: One of the adjustable numbers inside an AI model that are tuned during training. Large language models have billions of them, and together they store what the model has learned. to data so that it performs a tasktask (machine learning), n.: The job an AI model is meant to do, such as translating sentences, spotting spam or answering questions, defined by its inputs, its expected outputs and how success is scored. well, usually by minimizing a loss functionloss function, n.: A score that measures how wrong a model's predictions are. Training means adjusting the model, step by step, to push this number down. that measures its errors on training datatraining data, n.: The examples an AI system learns from. Whatever patterns, skills, gaps and biases are in the training data tend to show up in the finished system.. For neural networks this means many repeated steps of a forward passforward pass, n.: The step where a neural network takes an input and runs it through its layers, one after another, to produce an output — its answer or prediction., backpropagationbackpropagation, n.: The method neural networks use to learn from mistakes: it works backward from the error to figure out how much each internal connection contributed, so every connection can be adjusted in the right direction. of gradients and a parameter update by an optimizer such as stochastic gradient descentstochastic gradient descent, n.: A faster version of gradient descent that estimates which way is downhill from a small random sample of the training data at each step, instead of checking the whole dataset. or AdamAdam, prop. n.: The most widely used method for training neural networks. It smooths the direction of updates over time and automatically sets a separate step size for each setting based on how large its recent changes have been., over several epochsepoch, n.: One complete pass through all the training examples. Smaller models are often trained for many epochs, seeing each example many times; the largest language models may see most of their data only once. or, for large language models, roughly a single pass over trillions of tokenstoken, n.: The small chunk of text an AI language model reads and writes — often a word, part of a word or a punctuation mark. AI usage, limits and prices are counted in tokens.. Practitioners hold out validationvalidation set, n.: A set of examples kept out of training and used during development to compare model versions and settings, like a practice exam taken before the real one. and testtest set, n.: A set of examples kept completely apart from training and used at the end to measure how well a model works on data it has never seen, like a sealed final exam. data to detect overfittingoverfitting, n.: When a model learns its training examples too well — quirks and noise included — so it does great on data it has seen but poorly on anything new, like a student who memorizes answers without understanding. and tune hyperparametershyperparameter, n.: A setting chosen by people before training, such as how fast a model learns or how big it is, as opposed to the internal values the model learns by itself from data.. Large language models are trained in stages: pretrainingpretraining, n.: The first and usually the most expensive stage of building a modern AI model, in which it learns general patterns from enormous amounts of raw text, images or code before being specialized for particular uses. on broad data, then post-trainingpost-training, n.: Everything done to an AI model after its initial bulk training on huge amounts of text: the extra teaching that turns a raw text predictor into a helpful, safe assistant or a careful reasoner. such as supervised fine-tuningsupervised fine-tuning, n.: Teaching a pretrained AI model by showing it many examples of good answers to requests, so it learns to imitate them — like learning a job by studying worked examples. and reinforcement learning from human feedbackreinforcement learning from human feedback, n.: A way of training AI using people's judgments: humans compare pairs of answers, a scoring model learns their preferences, and the AI is then trained to produce answers that score well.. A single training run costs far more than answering any one query, but inferenceinference, n.: Drawing a conclusion from evidence. In today's AI it most often means running an already-trained model to get an answer, as opposed to training it. costs accumulate with every use.

Training took six weeks on 2,000 GPUs; the hard part was keeping the loss from spiking.