Update README.md

Corrected training examples from 1,500 to 5,000 to match the experiment done

README.md

@@ -26,7 +26,7 @@ It is **NOT** intended for factual information retrieval, professional advice, o
 
 ## Training Data
 
-The model was fine-tuned on 1,500 examples from the [krispyATL/pip-one](https://huggingface.co/datasets/krispyATL/pip-one) dataset, which contains user prompts paired with surreal, metaphorical responses. The training preserves the category distribution of the original dataset:
+The model was fine-tuned on 5,000 examples from the [krispyATL/pip-one](https://huggingface.co/datasets/krispyATL/pip-one) dataset, which contains user prompts paired with surreal, metaphorical responses. The training preserves the category distribution of the original dataset:
 
 - Scientific: 16.60%
 - Creative: 16.93%