update model card README.md

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8141
-- Rouge1: 10.3384
-- Rouge2: 5.4624
-- Rougel: 8.8777
-- Rougelsum: 9.8759
-- Gen Len: 19.999
+- Loss: 1.7853
+- Rouge1: 10.5621
+- Rouge2: 5.5959
+- Rougel: 9.0437
+- Rougelsum: 10.0264
+- Gen Len: 19.997
 
 ## Model description
 
@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.3299        | 1.0   | 2003 | 1.8141          | 10.3384 | 5.4624 | 8.8777 | 9.8759    | 19.999  |
+| 1.3444        | 1.0   | 2003 | 1.7853          | 10.5621 | 5.5959 | 9.0437 | 10.0264   | 19.997  |
 
 
 ### Framework versions