update model card README.md

README.md

@@ -32,7 +32,7 @@ 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: 0.7668
+- Loss: 0.7665
 - Accuracy: 0.9174
 
 ## Model description
@@ -64,16 +64,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 4.2879        | 1.0   | 318  | 3.2751          | 0.7248   |
-| 2.6115        | 2.0   | 636  | 1.8613          | 0.8374   |
-| 1.5334        | 3.0   | 954  | 1.1454          | 0.8981   |
-| 0.9992        | 4.0   | 1272 | 0.8480          | 0.9132   |
-| 0.7856        | 5.0   | 1590 | 0.7668          | 0.9174   |
+| 4.2879        | 1.0   | 318  | 3.2752          | 0.7239   |
+| 2.6117        | 2.0   | 636  | 1.8616          | 0.8365   |
+| 1.5335        | 3.0   | 954  | 1.1454          | 0.8987   |
+| 0.9992        | 4.0   | 1272 | 0.8479          | 0.9126   |
+| 0.7853        | 5.0   | 1590 | 0.7665          | 0.9174   |
 
 
 ### Framework versions
 
 - Transformers 4.31.0
 - Pytorch 2.0.1+cu117
-- Datasets 2.14.2
+- Datasets 2.10.1
 - Tokenizers 0.13.3