update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.5334876461854267
+      value: 0.10315004767907714
 ---
 
 <!-- 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: 0.7808
-- Matthews Correlation: 0.5335
+- Loss: 0.6976
+- Matthews Correlation: 0.1032
 
 ## Model description
 
@@ -63,16 +63,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5201        | 1.0   | 535  | 0.5173          | 0.4126               |
-| 0.3513        | 2.0   | 1070 | 0.5070          | 0.4864               |
-| 0.2373        | 3.0   | 1605 | 0.5830          | 0.5248               |
-| 0.1752        | 4.0   | 2140 | 0.7808          | 0.5335               |
-| 0.1312        | 5.0   | 2675 | 0.8111          | 0.5288               |
+| 0.6135        | 1.0   | 535  | 0.6257          | 0.0                  |
+| 0.6078        | 2.0   | 1070 | 0.6187          | 0.0                  |
+| 0.6038        | 3.0   | 1605 | 0.6179          | -0.0041              |
+| 0.5649        | 4.0   | 2140 | 0.6509          | 0.1006               |
+| 0.5093        | 5.0   | 2675 | 0.6976          | 0.1032               |
 
 
 ### Framework versions
 
-- Transformers 4.27.4
+- Transformers 4.29.0.dev0
 - Pytorch 1.13.1+cu116
-- Datasets 1.14.0
-- Tokenizers 0.13.3
+- Datasets 2.10.1
+- Tokenizers 0.13.2