update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.3335166592636138
+      value: 0.5536405531329313
 ---
 
 <!-- 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: 0.6697
-- Matthews Correlation: 0.3335
+- Loss: 0.8455
+- Matthews Correlation: 0.5536
 
 ## Model description
 
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| No log        | 1.0   | 54   | 0.5970          | 0.0                  |
-| No log        | 2.0   | 108  | 0.5601          | 0.3166               |
-| No log        | 3.0   | 162  | 0.6524          | 0.2803               |
-| No log        | 4.0   | 216  | 0.6697          | 0.3335               |
-| No log        | 5.0   | 270  | 0.6991          | 0.3305               |
+| 0.524         | 1.0   | 535  | 0.5547          | 0.3891               |
+| 0.3463        | 2.0   | 1070 | 0.5250          | 0.5011               |
+| 0.2329        | 3.0   | 1605 | 0.6321          | 0.5239               |
+| 0.1677        | 4.0   | 2140 | 0.7752          | 0.5372               |
+| 0.1197        | 5.0   | 2675 | 0.8455          | 0.5536               |
 
 
 ### Framework versions
 
-- Transformers 4.11.3
+- Transformers 4.12.3
 - Pytorch 1.9.0+cu111
-- Datasets 1.13.2
+- Datasets 1.15.1
 - Tokenizers 0.10.3