Training and Evaluation
Understand how Datature Vi trains vision-language models, what each setting controls, and how to measure your model's performance.
Datature Vi fine-tunes vision-language models (VLMs) on your annotated data. This section covers each stage of the training-to-inference pipeline: how to write system prompts that guide your model, what training settings control, how LoRA and quantization reduce cost, what evaluation metrics tell you, and how inference generates output.
In this section
What Are System Prompts?
How to instruct your model with role, focus, output format, and hallucination guards.
How Does VLM Training Work?
Epochs, batch size, learning rate, loss curves, and validation splits in plain language.
LoRA and Quantization
How LoRA reduces training cost and quantization shrinks memory. NF4, FP4, QLoRA explained.
How Do I Evaluate My Model?
IoU, F1, BLEU, BERTScore, and what good scores look like for phrase grounding and VQA.
How Does Inference Work?
Token generation, temperature, top-p, top-k, and how to control model output.
Next steps
Updated 6 days ago