update model card README.md

README.md

@@ -29,7 +29,7 @@ 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 clinc_oos dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7795
+- Loss: 0.7796
 - Accuracy: 0.9161
 
 ## Model description
@@ -62,16 +62,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 4.2938        | 1.0   | 318  | 3.2905          | 0.7406   |
-| 2.6346        | 2.0   | 636  | 1.8833          | 0.8323   |
-| 1.5554        | 3.0   | 954  | 1.1650          | 0.8923   |
+| 4.2938        | 1.0   | 318  | 3.2905          | 0.7410   |
+| 2.6346        | 2.0   | 636  | 1.8833          | 0.8326   |
+| 1.5554        | 3.0   | 954  | 1.1650          | 0.8926   |
 | 1.0189        | 4.0   | 1272 | 0.8636          | 0.9110   |
-| 0.8028        | 5.0   | 1590 | 0.7795          | 0.9161   |
+| 0.8028        | 5.0   | 1590 | 0.7796          | 0.9161   |
 
 
 ### Framework versions
 
-- Transformers 4.11.3
+- Transformers 4.18.0
 - Pytorch 1.11.0
 - Datasets 2.0.0
-- Tokenizers 0.10.3
+- Tokenizers 0.12.1