update model card README.md

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1660
-- Accuracy: 0.7383
-- Qwk: 0.6751
+- Loss: 2.1865
+- Accuracy: 0.7300
+- Qwk: 0.6937
 
 ## Model description
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Qwk    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 91   | 2.1660          | 0.7383   | 0.6751 |
-| No log        | 2.0   | 182  | 1.9587          | 0.7218   | 0.6607 |
-| No log        | 3.0   | 273  | 2.3844          | 0.7052   | 0.6725 |
-| No log        | 4.0   | 364  | 2.2337          | 0.7135   | 0.6798 |
-| No log        | 5.0   | 455  | 2.1919          | 0.7245   | 0.6838 |
+| No log        | 1.0   | 91   | 2.3480          | 0.7245   | 0.6519 |
+| No log        | 2.0   | 182  | 2.1615          | 0.7273   | 0.6827 |
+| No log        | 3.0   | 273  | 2.2337          | 0.7107   | 0.6739 |
+| No log        | 4.0   | 364  | 2.1598          | 0.7218   | 0.7019 |
+| No log        | 5.0   | 455  | 2.1865          | 0.7300   | 0.6937 |
 
 
 ### Framework versions