update model card README.md

tiny-mbart-quechua/README.md

@@ -2,6 +2,8 @@
 tags:
 - simplification
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: tiny-mbart-quechua
   results: []
@@ -13,6 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 # tiny-mbart-quechua
 
 This model is a fine-tuned version of [sshleifer/tiny-mbart](https://huggingface.co/sshleifer/tiny-mbart) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.8454
+- Bleu: 0.0
+- Gen Len: 20.0
 
 ## Model description
 
@@ -39,6 +45,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 2
 
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:----:|:-------:|
+| 5.9674        | 1.0   | 25687 | 5.9599          | 0.0  | 20.0    |
+| 5.8352        | 2.0   | 51374 | 5.8454          | 0.0  | 20.0    |
+
+
 ### Framework versions
 
 - Transformers 4.26.1