update model card README.md

README.md

@@ -4,8 +4,6 @@ tags:
 - generated_from_trainer
 metrics:
 - accuracy
-widget:
-- '全国高校科研质量排名，清华北大浙大无缘前五'
 model-index:
 - name: classification_tnews_arg
   results: []
@@ -18,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [hfl/chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0381
-- Accuracy: 0.5267
+- Loss: 1.1794
+- Accuracy: 0.7133
 
 ## Model description
 
@@ -50,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4261        | 1.0   | 150  | 1.7956          | 0.52     |
-| 0.1893        | 2.0   | 300  | 1.9534          | 0.54     |
-| 0.0475        | 3.0   | 450  | 2.0381          | 0.5267   |
+| 1.3992        | 1.0   | 150  | 1.2185          | 0.66     |
+| 0.1415        | 2.0   | 300  | 1.1324          | 0.6933   |
+| 0.0376        | 3.0   | 450  | 1.1794          | 0.7133   |
 
 
 ### Framework versions