update model card README.md

README.md

@@ -16,8 +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: 0.1239
-- Accuracy: 1.0
+- Loss: 0.6526
+- Accuracy: 0.55
 
 ## Model description
 
@@ -42,20 +42,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6943        | 1.0   | 10   | 0.6270          | 0.7      |
-| 0.5577        | 2.0   | 20   | 0.5745          | 0.65     |
-| 0.38          | 3.0   | 30   | 0.4222          | 0.8      |
-| 0.2391        | 4.0   | 40   | 0.2934          | 0.95     |
-| 0.1461        | 5.0   | 50   | 0.2122          | 0.95     |
-| 0.0845        | 6.0   | 60   | 0.1638          | 1.0      |
-| 0.0631        | 7.0   | 70   | 0.1347          | 1.0      |
-| 0.0479        | 8.0   | 80   | 0.1239          | 1.0      |
+| 0.7902        | 1.0   | 2    | 0.7168          | 0.45     |
+| 0.5889        | 2.0   | 4    | 0.7072          | 0.5      |
+| 0.4923        | 3.0   | 6    | 0.7051          | 0.4      |
+| 0.4312        | 4.0   | 8    | 0.6980          | 0.5      |
+| 0.4024        | 5.0   | 10   | 0.6852          | 0.55     |
+| 0.3531        | 6.0   | 12   | 0.6776          | 0.6      |
+| 0.3262        | 7.0   | 14   | 0.6674          | 0.6      |
+| 0.2734        | 8.0   | 16   | 0.6608          | 0.6      |
+| 0.2593        | 9.0   | 18   | 0.6559          | 0.55     |
+| 0.2336        | 10.0  | 20   | 0.6526          | 0.55     |
 
 
 ### Framework versions