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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1633
-- Accuracy: 0.9581
+- Loss: 0.1466
+- Accuracy: 0.9611
 
 ## Model description
 
@@ -48,11 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 48   | 0.5885          | 0.8503   |
-| No log        | 2.0   | 96   | 0.3185          | 0.9251   |
-| No log        | 3.0   | 144  | 0.2298          | 0.9311   |
-| No log        | 4.0   | 192  | 0.1811          | 0.9491   |
-| No log        | 5.0   | 240  | 0.1633          | 0.9581   |
+| No log        | 1.0   | 48   | 0.5105          | 0.8623   |
+| No log        | 2.0   | 96   | 0.2715          | 0.9281   |
+| No log        | 3.0   | 144  | 0.1998          | 0.9431   |
+| No log        | 4.0   | 192  | 0.1466          | 0.9611   |
+| No log        | 5.0   | 240  | 0.1408          | 0.9581   |
 
 
 ### Framework versions