update model card README.md

README.md

@@ -16,12 +16,12 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5628
-- Rouge1: 0.2526
-- Rouge2: 0.0768
-- Rougel: 0.2107
-- Rougelsum: 0.2092
-- Gen Len: 18.7907
+- Loss: 2.5913
+- Rouge1: 0.2669
+- Rouge2: 0.0813
+- Rougel: 0.2091
+- Rougelsum: 0.2096
+- Gen Len: 18.3256
 
 ## Model description
 
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 99   | 2.5303          | 0.2381 | 0.0804 | 0.1919 | 0.1908    | 18.4651 |
-| No log        | 2.0   | 198  | 2.5241          | 0.2623 | 0.0922 | 0.2162 | 0.2144    | 19.1395 |
-| No log        | 3.0   | 297  | 2.5326          | 0.2481 | 0.0879 | 0.2043 | 0.204     | 18.0233 |
-| No log        | 4.0   | 396  | 2.5628          | 0.2526 | 0.0768 | 0.2107 | 0.2092    | 18.7907 |
+| No log        | 1.0   | 99   | 2.5765          | 0.2465 | 0.081  | 0.2005 | 0.2009    | 18.0465 |
+| No log        | 2.0   | 198  | 2.5323          | 0.2378 | 0.0797 | 0.1953 | 0.1959    | 17.2326 |
+| No log        | 3.0   | 297  | 2.5939          | 0.2646 | 0.0882 | 0.2133 | 0.2134    | 19.6744 |
+| No log        | 4.0   | 396  | 2.5913          | 0.2669 | 0.0813 | 0.2091 | 0.2096    | 18.3256 |
 
 
 ### Framework versions