update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9470967741935484
+      value: 0.9448387096774193
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ 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 clinc_oos dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3180
-- Accuracy: 0.9471
+- Loss: 0.1894
+- Accuracy: 0.9448
 
 ## Model description
 
@@ -63,21 +63,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.8197        | 1.0   | 318  | 2.0528          | 0.7435   |
-| 1.5825        | 2.0   | 636  | 1.0403          | 0.8684   |
-| 0.8215        | 3.0   | 954  | 0.5924          | 0.9110   |
-| 0.486         | 4.0   | 1272 | 0.4252          | 0.9345   |
-| 0.3488        | 5.0   | 1590 | 0.3693          | 0.9452   |
-| 0.2872        | 6.0   | 1908 | 0.3440          | 0.9452   |
-| 0.2564        | 7.0   | 2226 | 0.3297          | 0.9468   |
-| 0.2393        | 8.0   | 2544 | 0.3241          | 0.9465   |
-| 0.2317        | 9.0   | 2862 | 0.3208          | 0.9471   |
-| 0.2265        | 10.0  | 3180 | 0.3180          | 0.9471   |
+| 1.6133        | 1.0   | 318  | 1.0679          | 0.7290   |
+| 0.8231        | 2.0   | 636  | 0.5164          | 0.8652   |
+| 0.4289        | 3.0   | 954  | 0.3019          | 0.9168   |
+| 0.2722        | 4.0   | 1272 | 0.2336          | 0.9335   |
+| 0.214         | 5.0   | 1590 | 0.2117          | 0.94     |
+| 0.1914        | 6.0   | 1908 | 0.2007          | 0.9445   |
+| 0.1785        | 7.0   | 2226 | 0.1947          | 0.9435   |
+| 0.1716        | 8.0   | 2544 | 0.1919          | 0.9468   |
+| 0.1674        | 9.0   | 2862 | 0.1901          | 0.9452   |
+| 0.1659        | 10.0  | 3180 | 0.1894          | 0.9448   |
 
 
 ### Framework versions
 
-- Transformers 4.22.2
-- Pytorch 1.12.1+cu113
-- Datasets 2.5.1
-- Tokenizers 0.12.1
+- Transformers 4.25.1
+- Pytorch 1.13.0+cu116
+- Datasets 2.8.0
+- Tokenizers 0.13.2