update model card README.md

README.md

@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # reformer-big_patent-16384
 
-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.
+This model was trained from scratch on the big_patent dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.2894
+- Loss: 6.1465
 
 ## Model description
 
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 6.3321        | 1.0   | 17732 | 6.3799          |
-| 6.2519        | 2.0   | 35464 | 6.3086          |
-| 6.2184        | 3.0   | 53196 | 6.2894          |
+| 6.1432        | 1.0   | 17732 | 6.2011          |
+| 6.0925        | 2.0   | 35464 | 6.1784          |
+| 6.078         | 3.0   | 53196 | 6.1465          |
 
 
 ### Framework versions