update model card README.md

README.md

@@ -20,7 +20,7 @@ model-index:
     metrics:
     - name: Pearsonr
       type: pearsonr
-      value: 0.8792156464193064
+      value: 0.8823459724851859
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,8 +30,8 @@ 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: 0.5353
-- Pearsonr: 0.8792
+- Loss: 0.5543
+- Pearsonr: 0.8823
 
 ## Model description
 
@@ -62,11 +62,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Pearsonr |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 46   | 0.8265          | 0.8153   |
-| No log        | 2.0   | 92   | 0.8016          | 0.8500   |
-| No log        | 3.0   | 138  | 0.6058          | 0.8729   |
-| No log        | 4.0   | 184  | 0.5353          | 0.8792   |
-| No log        | 5.0   | 230  | 0.5959          | 0.8763   |
+| No log        | 1.0   | 46   | 0.6248          | 0.8466   |
+| No log        | 2.0   | 92   | 0.5657          | 0.8710   |
+| No log        | 3.0   | 138  | 0.5442          | 0.8801   |
+| No log        | 4.0   | 184  | 0.5262          | 0.8823   |
+| No log        | 5.0   | 230  | 0.5543          | 0.8823   |
 
 
 ### Framework versions