update model card README.md

README.md

@@ -11,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # GWW
 
-This model is a fine-tuned version of [GroNLP/bert-base-dutch-cased](https://huggingface.co/GroNLP/bert-base-dutch-cased) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7144
+- Loss: 3.5146
 
 ## Model description
 
@@ -45,11 +45,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.1537        | 1.0   | 50   | 3.2586          |
-| 3.3257        | 2.0   | 100  | 3.0064          |
-| 3.1152        | 3.0   | 150  | 2.8890          |
-| 2.9988        | 4.0   | 200  | 2.8521          |
-| 2.9437        | 5.0   | 250  | 2.7453          |
+| 5.9035        | 1.0   | 111  | 4.6639          |
+| 4.419         | 2.0   | 222  | 4.0245          |
+| 4.0005        | 3.0   | 333  | 3.7153          |
+| 3.771         | 4.0   | 444  | 3.5667          |
+| 3.6898        | 5.0   | 555  | 3.5200          |
 
 
 ### Framework versions