update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.5303243504311796
+      value: 0.5340667882909217
 ---
 
 <!-- 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: 0.7201
-- Matthews Correlation: 0.5303
+- Loss: 0.8951
+- Matthews Correlation: 0.5341
 
 ## Model description
 
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5297        | 1.0   | 535  | 0.4998          | 0.4239               |
-| 0.3558        | 2.0   | 1070 | 0.5067          | 0.5022               |
-| 0.2426        | 3.0   | 1605 | 0.6199          | 0.5067               |
-| 0.1863        | 4.0   | 2140 | 0.7201          | 0.5303               |
-| 0.1266        | 5.0   | 2675 | 0.8710          | 0.5143               |
+| 0.5228        | 1.0   | 535  | 0.5433          | 0.3978               |
+| 0.3485        | 2.0   | 1070 | 0.5720          | 0.4775               |
+| 0.2365        | 3.0   | 1605 | 0.6897          | 0.5014               |
+| 0.1707        | 4.0   | 2140 | 0.7869          | 0.5086               |
+| 0.1301        | 5.0   | 2675 | 0.8951          | 0.5341               |
 
 
 ### Framework versions
 
-- Transformers 4.17.0
+- Transformers 4.18.0
 - Pytorch 1.10.0+cu111
 - Datasets 2.0.0
-- Tokenizers 0.12.0
+- Tokenizers 0.11.6