update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.947741935483871
+      value: 0.9196774193548387
 ---
 
 <!-- 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: 0.2641
-- Accuracy: 0.9477
+- Loss: 0.7676
+- Accuracy: 0.9197
 
 ## Model description
 
@@ -63,11 +63,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0141        | 1.0   | 318  | 0.2389          | 0.9487   |
-| 0.0083        | 2.0   | 636  | 0.2485          | 0.9490   |
-| 0.0063        | 3.0   | 954  | 0.2574          | 0.9481   |
-| 0.0043        | 4.0   | 1272 | 0.2641          | 0.9477   |
-| 0.0038        | 5.0   | 1590 | 0.2641          | 0.9477   |
+| 4.2865        | 1.0   | 318  | 3.2873          | 0.7403   |
+| 2.634         | 2.0   | 636  | 1.8787          | 0.8552   |
+| 1.549         | 3.0   | 954  | 1.1519          | 0.8981   |
+| 1.0026        | 4.0   | 1272 | 0.8497          | 0.9184   |
+| 0.7886        | 5.0   | 1590 | 0.7676          | 0.9197   |
 
 
 ### Framework versions