update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.5387376669923544
+      value: 0.5291140309961344
 ---
 
 <!-- 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 glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5531
-- Matthews Correlation: 0.5387
+- Loss: 0.8252
+- Matthews Correlation: 0.5291
 
 ## Model description
 
@@ -63,16 +63,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5305        | 1.0   | 535  | 0.5387          | 0.3885               |
-| 0.352         | 2.0   | 1070 | 0.5164          | 0.4831               |
-| 0.2381        | 3.0   | 1605 | 0.5531          | 0.5387               |
-| 0.1815        | 4.0   | 2140 | 0.7291          | 0.5314               |
-| 0.1227        | 5.0   | 2675 | 0.8387          | 0.5268               |
+| 0.5226        | 1.0   | 535  | 0.5248          | 0.4151               |
+| 0.3447        | 2.0   | 1070 | 0.4926          | 0.5082               |
+| 0.2294        | 3.0   | 1605 | 0.5572          | 0.5196               |
+| 0.1804        | 4.0   | 2140 | 0.7923          | 0.4975               |
+| 0.1366        | 5.0   | 2675 | 0.8252          | 0.5291               |
 
 
 ### Framework versions
 
 - Transformers 4.26.1
-- Pytorch 1.13.1
+- Pytorch 1.13.1+cu116
 - Datasets 2.9.0
 - Tokenizers 0.13.2