update text

introduction.md

@@ -119,6 +119,18 @@ didn't go well. Eventually, the thing that worked out the best was fixing the lo
 is used after the computation of the similarity between the images and the texts in CLIP (see the code [here](https://github.com/clip-italian/clip-italian/blob/master/hybrid_clip/modeling_hybrid_clip.py#L64)).
 We got this idea from Nils' [video](https://youtu.be/RHXZKUr8qOY) on sentence embeddings.
 
+### Effect
+
+The following picture showcase the effect that this edits have had on our loss:
+
+<img src="https://huggingface.co/spaces/clip-italian/clip-italian-demo/raw/main/static/img/improvements.png" alt="drawing" width="600"/>
+
+The purple line is the original training, you can see how many steps we needed to get the loss down. Yellow line is the
+loss with the new optimizer, it is **striking** to see the time we save from this addition! Blue line shows the results when
+fixed scaling is added with the new optimization. Finally, we added the backbone freezing part and you can see the
+results in the light blue loss. 
+
+
 # Scientific Validity
 
 ## Quantitative Evaluation