update model card README.md

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the snips_built_in_intents dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2339
+- Loss: 0.2158
 - Accuracy: 1.0
 
 ## Model description
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9236        | 1.0   | 37   | 1.6689          | 0.3667   |
-| 0.9259        | 2.0   | 74   | 0.7197          | 0.8333   |
-| 0.4666        | 3.0   | 111  | 0.2339          | 1.0      |
-| 0.1732        | 4.0   | 148  | 0.1144          | 1.0      |
-| 0.1412        | 5.0   | 185  | 0.0724          | 1.0      |
-| 0.1023        | 6.0   | 222  | 0.0536          | 1.0      |
-| 0.0772        | 7.0   | 259  | 0.0453          | 1.0      |
-| 0.0786        | 8.0   | 296  | 0.0396          | 1.0      |
-| 0.0581        | 9.0   | 333  | 0.0374          | 1.0      |
-| 0.0553        | 10.0  | 370  | 0.0364          | 1.0      |
+| 1.7528        | 1.0   | 37   | 1.5430          | 0.4      |
+| 0.4361        | 2.0   | 74   | 0.6562          | 0.8667   |
+| 0.2656        | 3.0   | 111  | 0.2158          | 1.0      |
+| 0.1121        | 4.0   | 148  | 0.1056          | 1.0      |
+| 0.1295        | 5.0   | 185  | 0.0753          | 1.0      |
+| 0.0897        | 6.0   | 222  | 0.0554          | 1.0      |
+| 0.0704        | 7.0   | 259  | 0.0467          | 1.0      |
+| 0.0638        | 8.0   | 296  | 0.0420          | 1.0      |
+| 0.047         | 9.0   | 333  | 0.0393          | 1.0      |
+| 0.0632        | 10.0  | 370  | 0.0387          | 1.0      |
 
 
 ### Framework versions