Update README.md

README.md

@@ -29,7 +29,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-artworkclassifier
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. This is a subset of the artbench-10 dataset, with a train set of 1000 artworks per class and a test set of 100 artworks per class.
 It achieves the following results on the evaluation set:
 - Loss: 1.1392
 - Accuracy: 0.5948