update model card README.md

README.md

@@ -22,10 +22,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9385
+      value: 0.935
     - name: F1
       type: f1
-      value: 0.9386094184311659
+      value: 0.9351083637430424
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ 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 emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1635
-- Accuracy: 0.9385
-- F1: 0.9386
+- Loss: 0.1582
+- Accuracy: 0.935
+- F1: 0.9351
 
 ## Model description
 
@@ -68,10 +68,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.1408        | 1.0   | 250  | 0.1685          | 0.93     | 0.9293 |
-| 0.0895        | 2.0   | 500  | 0.1563          | 0.936    | 0.9356 |
-| 0.0758        | 3.0   | 750  | 0.1568          | 0.9385   | 0.9388 |
-| 0.0663        | 4.0   | 1000 | 0.1635          | 0.9385   | 0.9386 |
+| 0.7703        | 1.0   | 250  | 0.2588          | 0.918    | 0.9165 |
+| 0.2031        | 2.0   | 500  | 0.1773          | 0.928    | 0.9282 |
+| 0.1385        | 3.0   | 750  | 0.1593          | 0.934    | 0.9342 |
+| 0.1101        | 4.0   | 1000 | 0.1582          | 0.935    | 0.9351 |
 
 
 ### Framework versions