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: 1.7962
-- Rouge1: 10.5084
-- Rouge2: 5.5784
-- Rougel: 9.0804
-- Rougelsum: 10.0489
+- Loss: 1.8015
+- Rouge1: 10.6584
+- Rouge2: 5.6201
+- Rougel: 9.0991
+- Rougelsum: 10.0916
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.3055        | 1.0   | 2003 | 1.7962          | 10.5084 | 5.5784 | 9.0804 | 10.0489   | 20.0    |
+| 1.2807        | 1.0   | 2003 | 1.8015          | 10.6584 | 5.6201 | 9.0991 | 10.0916   | 20.0    |
 
 
 ### Framework versions