Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 language: 
-- 
+- English
 -
 thumbnail: 
 tags:
@@ -9,21 +9,21 @@ tags:
 - 
 license: 
 datasets:
-- 
+- XSUM, Gigaword
 -
 metrics:
-- 
+- Rouge
 -
 ---
 
-# MyModelName
+# Pegasus XSUM Gigaword
 
 ## Model description
 
-You can embed local or remote images using `![](...)`
+Pegasus XSUM model finetuned to Gigaword Summarization task 
 
 ## Intended uses & limitations
-
+Produces short summaries with the coherence of the XSUM Model
 #### How to use
 
 ```python
@@ -32,18 +32,21 @@ You can embed local or remote images using `![](...)`
 
 #### Limitations and bias
 
-Provide examples of latent issues and potential remediations.
-
+Still has all the biases of any of the abstractive models, but seems a little less prone to hallucination. 
 ## Training data
 
-Describe the data you used to train the model.
-If you initialized it with pre-trained weights, add a link to the pre-trained model card or repository with description of the pre-training data.
+Initialized with pegasus-XSUM
 
 ## Training procedure
 
-Preprocessing, hardware used, hyperparameters...
+Trained for 11500 iterations on Gigaword corpus using OOB seq2seq (from hugging face using the default parameters)
 
 ## Eval results
+Evaluated on Gigaword evaluation set (from hugging face using the default parameters)
+eval_rouge1               =  47.8218
+eval_rouge2               =  23.1533
+eval_rougeL               =   44.341
+eval_rougeLsum            =  44.3198
 
 ### BibTeX entry and citation info