Update README.md

README.md

@@ -12,21 +12,25 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Clickbait1
 
-This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset.
+This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the [Webis-Clickbait-17](https://zenodo.org/record/5530410) dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0260
 
 ## Model description
 
-More information needed
+MiniLM is a distilled model from the paper "MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers".
+
+We fine tune this model to evaluate (regression) the clickbait level of a title news.
 
 ## Intended uses & limitations
 
-More information needed
+Model was designed to test the possibilities of Transformers in this cas of NLP problem (like in the paper  "Predicting Clickbait Strength in Online Social Media" by Indurthi Vijayasaradhi, Syed Bakhtiyar, Gupta Manish, Varma Vasudeva).
+
+The model wa trained in english.
 
 ## Training and evaluation data
 
-More information needed
+We train the model with the official training data of the chalenge, plus another set that was available after the end of the challenge.
 
 ## Training procedure