update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9409677419354838
+      value: 0.8274193548387097
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ 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: 0.1647
-- Accuracy: 0.9410
+- Loss: 1.9706
+- Accuracy: 0.8274
 
 ## Model description
 
@@ -55,21 +55,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 9
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4177        | 1.0   | 318  | 0.9041          | 0.72     |
-| 0.6997        | 2.0   | 636  | 0.4302          | 0.8590   |
-| 0.3645        | 3.0   | 954  | 0.2544          | 0.9139   |
-| 0.2365        | 4.0   | 1272 | 0.1990          | 0.9345   |
-| 0.1907        | 5.0   | 1590 | 0.1808          | 0.9394   |
-| 0.1713        | 6.0   | 1908 | 0.1726          | 0.9394   |
-| 0.1612        | 7.0   | 2226 | 0.1681          | 0.9406   |
-| 0.1558        | 8.0   | 2544 | 0.1652          | 0.9410   |
-| 0.1529        | 9.0   | 2862 | 0.1647          | 0.9410   |
+| 4.202         | 1.0   | 318  | 3.3225          | 0.7248   |
+| 2.8372        | 2.0   | 636  | 2.2856          | 0.8061   |
+| 2.1626        | 3.0   | 954  | 1.9706          | 0.8274   |
 
 
 ### Framework versions