OpenAI Dev
Home/Prompting

Prompting

Tips, techniques, and best practices for prompt engineering across all OpenAI models.

Topic
Training data format for function calling fine-tuning
fine-tuningfunction-callingtraining-data

I'm trying to finetune a model to be better at function calling for my specific use case but I'm struggling with the training data format. The docs s

Evaluating fine-tuned models: Beyond loss metrics
fine-tuningevaluationmetrics

Training loss going down doesn't mean your finetuned model is actually better. I've learned this the hard way. Evaluation framework I use 1. Tasksp

Cost of fine-tuning vs in-context learning at scale
fine-tuningcostenterprise

We ran the numbers on finetuning GPT4omini vs using fewshot prompting with GPT4o for our classification task 10K requests/day. Option A: Fewshot GPT

Fine-tuning GPT-4o-mini for SQL generation - results and tips
fine-tuningsqlgpt-4o-mini

I finetuned GPT4omini to generate SQL queries for our specific database schema and the results are impressive. Sharing my approach. Dataset 3,200 q

DPO fine-tuning now available - first impressions
fine-tuningdporlhf

OpenAI recently added Direct Preference Optimization DPO to the finetuning API. I've been testing it for preference alignment and here are my first im

Fine-tuned model performance degradation after 3 epochs
fine-tuningoverfittingepochs

I'm finetuning GPT4omini on a customer service dataset 5000 examples and seeing performance peak at epoch 23, then degrade significantly. Training m