update model card README.md

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [robingeibel/reformer-finetuned-big_patent-wikipedia-arxiv-16384](https://huggingface.co/robingeibel/reformer-finetuned-big_patent-wikipedia-arxiv-16384) on the big_patent dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.5256
+- Loss: 6.2894
 
 ## Model description
 
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 6.5993        | 1.0   | 17732 | 6.6557          |
-| 6.4838        | 2.0   | 35464 | 6.5458          |
-| 6.4558        | 3.0   | 53196 | 6.5256          |
+| 6.3321        | 1.0   | 17732 | 6.3799          |
+| 6.2519        | 2.0   | 35464 | 6.3086          |
+| 6.2184        | 3.0   | 53196 | 6.2894          |
 
 
 ### Framework versions