update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.5546789239242798
+      value: 0.541356878970505
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ 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: 0.8564
-- Matthews Correlation: 0.5547
+- Loss: 0.7470
+- Matthews Correlation: 0.5414
 
 ## Model description
 
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5209        | 1.0   | 535  | 0.5371          | 0.4251               |
-| 0.3454        | 2.0   | 1070 | 0.5160          | 0.5233               |
-| 0.2348        | 3.0   | 1605 | 0.6385          | 0.5121               |
-| 0.1684        | 4.0   | 2140 | 0.7436          | 0.5504               |
-| 0.1244        | 5.0   | 2675 | 0.8564          | 0.5547               |
+| 0.5237        | 1.0   | 535  | 0.5327          | 0.4248               |
+| 0.347         | 2.0   | 1070 | 0.5105          | 0.5239               |
+| 0.2344        | 3.0   | 1605 | 0.6639          | 0.5224               |
+| 0.1672        | 4.0   | 2140 | 0.7470          | 0.5414               |
+| 0.1228        | 5.0   | 2675 | 0.8352          | 0.5377               |
 
 
 ### Framework versions
 
-- Transformers 4.11.3
+- Transformers 4.12.2
 - Pytorch 1.9.0+cu111
 - Datasets 1.14.0
 - Tokenizers 0.10.3