update model card README.md

README.md

@@ -16,8 +16,8 @@ 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: 0.6393
-- Accuracy: 0.75
+- Loss: 0.6158
+- Accuracy: 0.6
 
 ## Model description
 
@@ -48,11 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 1    | 0.6393          | 0.75     |
-| No log        | 2.0   | 2    | 0.6337          | 0.75     |
-| No log        | 3.0   | 3    | 0.6298          | 0.75     |
-| No log        | 4.0   | 4    | 0.6256          | 0.75     |
-| No log        | 5.0   | 5    | 0.6239          | 0.75     |
+| No log        | 1.0   | 1    | 0.6158          | 0.6      |
+| No log        | 2.0   | 2    | 0.6023          | 0.6      |
+| No log        | 3.0   | 3    | 0.5961          | 0.6      |
+| No log        | 4.0   | 4    | 0.5907          | 0.6      |
+| No log        | 5.0   | 5    | 0.5870          | 0.6      |
 
 
 ### Framework versions