update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8480300187617261
+      value: 0.8395872420262664
     - name: F1
       type: f1
-      value: 0.8480214592727926
+      value: 0.8395554737965957
     - name: Precision
       type: precision
-      value: 0.8481084411583488
+      value: 0.8398564101118846
     - name: Recall
       type: recall
-      value: 0.8480300187617261
+      value: 0.8395872420262664
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ 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 rotten_tomatoes_movie_review dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4452
-- Accuracy: 0.8480
-- F1: 0.8480
-- Precision: 0.8481
-- Recall: 0.8480
+- Loss: 0.4438
+- Accuracy: 0.8396
+- F1: 0.8396
+- Precision: 0.8399
+- Recall: 0.8396
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| No log        | 1.0   | 267  | 0.4094          | 0.8246   | 0.8241 | 0.8281    | 0.8246 |
-| 0.3518        | 2.0   | 534  | 0.4000          | 0.8508   | 0.8508 | 0.8510    | 0.8508 |
-| 0.3518        | 3.0   | 801  | 0.4452          | 0.8480   | 0.8480 | 0.8481    | 0.8480 |
+| No log        | 1.0   | 267  | 0.4091          | 0.8236   | 0.8232 | 0.8270    | 0.8236 |
+| 0.3608        | 2.0   | 534  | 0.3945          | 0.8405   | 0.8405 | 0.8406    | 0.8405 |
+| 0.3608        | 3.0   | 801  | 0.4438          | 0.8396   | 0.8396 | 0.8399    | 0.8396 |
 
 
 ### Framework versions