Añadidos tags

README.md

@@ -11,43 +11,50 @@ datasets:
 - larazonpublico
 - es
 metrics:
-- ROUGE-1
-- ROUGE-2
+- rouge
 ---
 
 # mt5-small-spanish-summarization
 
 ## Model description
 
-You can embed local or remote images using `![](...)`
+This is a mt5-small model finetuned for generating headlines from the body of the news in Spanish. 
 
-## Intended uses & limitations
+## Training data
 
-#### How to use
+The model was trained with 58425 news extracted from the La Raz�n (31477) and P�blico (26948) newspapers. These news belong to the following categories: "Espa�a", "Cultura", "Econom�a", "Igualdad" and "Pol�tica".
 
-```python
-# You can include sample code which will be formatted
-```
+## Training procedure
 
-#### Limitations and bias
+It was trained with Google Colab's GPU Tesla P100-PCIE-16GB for 2 epochs.
 
-Provide examples of latent issues and potential remediations.
+### Hyperparameters
 
-## Training data
+{evaluation_strategy = "epoch",
+learning_rate = 2e-4,
+per_device_train_batch_size = 6,
+per_device_eval_batch_size = 6,
+weight_decay = 0.01,
+save_total_limi t= 3,
+num_train_epochs = 2,
+predict_with_generate = True,
+fp16 = False}
 
-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.
-
-## Training procedure
-
-Preprocessing, hardware used, hyperparameters...
 
 ## Eval results
+| metric | score |
+| --- | ----- |
+| rouge1 | 44.03 |
+| rouge2 | 28.2900 |
+| rougeL | 40.54 |
+| rougeLsum | 40.5587 |
+
 
 ### BibTeX entry and citation info
 
 ```bibtex
-@inproceedings{...,
-  year={2020}
+@inproceedings{ mt5lrpjosmunpen,
+  year={2020},
+  author = {Jos� Manuel Mu�iz Pe�a},
 }
 ```