Skip to content
masterclass Buddy
Start learning

AI & ML · Concept

Learning Rate

A learning-rate multiplier controls the size of parameter updates during fine-tuning. Start with the default, then increase it if the model does not appear to converge.

Last updated

Syntax

method.supervised.hyperparameters.learning_rate_multiplier

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • Fine-tuning
  • Hyperparameters
  • Epochs
  • Batch size
  • Supervised fine-tuning

Source: Fine-tuning best practices | OpenAI API. Checked 2026-11-03.