include warnings

README.md

@@ -16,10 +16,12 @@ This is a [SetFit model](https://github.com/huggingface/setfit) that can be used
 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
 2. Training a classification head with features from the fine-tuned Sentence Transformer.
 
-Accuracy on a number of experiments can be found in the figure below.
+Accuracy on a number of experiments on a minimal test set (35 examples) can be found in the figure below.
 
 ![plot](./emotional_accuracy.svg)
 
+Please note that these results are not a good representation of the model's actual performance. As previously stated, the test set is tiny and the examples in that test set are cherry picked. This model will be properly evaluated on real life data at a later time.
+
 Id to emotional label schema is as follows:
 
 ```