update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.5834885164494104
+      value: 0.5973782771535581
     - name: Recall
       type: recall
-      value: 0.6555090655509066
+      value: 0.6673640167364017
     - name: F1
       type: f1
-      value: 0.6174055829228243
+      value: 0.6304347826086957
     - name: Accuracy
       type: accuracy
-      value: 0.9235426702611924
+      value: 0.9227913554602908
 ---
 
 <!-- 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 [klue/bert-base](https://huggingface.co/klue/bert-base) on the klue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2397
-- Precision: 0.5835
-- Recall: 0.6555
-- F1: 0.6174
-- Accuracy: 0.9235
+- Loss: 0.2382
+- Precision: 0.5974
+- Recall: 0.6674
+- F1: 0.6304
+- Accuracy: 0.9228
 
 ## Model description
 
@@ -78,8 +78,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 313  | 0.2569          | 0.5378    | 0.6297 | 0.5801 | 0.9190   |
-| 0.3194        | 2.0   | 626  | 0.2397          | 0.5835    | 0.6555 | 0.6174 | 0.9235   |
+| No log        | 1.0   | 313  | 0.2539          | 0.5534    | 0.6395 | 0.5933 | 0.9205   |
+| 0.3052        | 2.0   | 626  | 0.2382          | 0.5974    | 0.6674 | 0.6304 | 0.9228   |
 
 
 ### Framework versions