update model card README.md

README.md

@@ -17,11 +17,11 @@ 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: 1.8156
-- Rouge1: 10.6283
-- Rouge2: 5.446
-- Rougel: 9.0505
-- Rougelsum: 10.1603
+- Loss: 1.8239
+- Rouge1: 10.4203
+- Rouge2: 5.4986
+- Rougel: 8.9779
+- Rougelsum: 9.9702
 - Gen Len: 20.0
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.2443        | 1.0   | 2003 | 1.8156          | 10.6283 | 5.446  | 9.0505 | 10.1603   | 20.0    |
+| 1.1654        | 1.0   | 2003 | 1.8239          | 10.4203 | 5.4986 | 8.9779 | 9.9702    | 20.0    |
 
 
 ### Framework versions