Skip to content
masterclass Buddy
Start learning

AI & ML · Concept

Overfitting

Fine-tuning checkpoints are model versions saved during training. They let you test earlier versions and choose one that performs better before overfitting.

Last updated

Syntax

GET /v1/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

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

Subscribe
  • fine-tuning jobs
  • fine_tuned_model_checkpoint
  • step_number
  • metrics
  • full_valid_loss
  • full_valid_mean_token_accuracy
  • overfitting

Source: Supervised fine-tuning | OpenAI API. Checked 2026-11-03.