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: 0.0747
-- Accuracy: 0.95
+- Loss: 0.4231
+- Accuracy: 0.8
 
 ## Model description
 
@@ -42,22 +42,17 @@ 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: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7667        | 1.0   | 10   | 0.6008          | 0.8      |
-| 0.4889        | 2.0   | 20   | 0.4180          | 0.85     |
-| 0.2702        | 3.0   | 30   | 0.2567          | 0.9      |
-| 0.1223        | 4.0   | 40   | 0.1469          | 0.95     |
-| 0.0547        | 5.0   | 50   | 0.0753          | 1.0      |
-| 0.0279        | 6.0   | 60   | 0.0770          | 0.95     |
-| 0.0154        | 7.0   | 70   | 0.0955          | 0.95     |
-| 0.0103        | 8.0   | 80   | 0.0847          | 0.95     |
-| 0.0083        | 9.0   | 90   | 0.0760          | 0.95     |
-| 0.0077        | 10.0  | 100  | 0.0747          | 0.95     |
+| 0.6966        | 1.0   | 10   | 0.6687          | 0.65     |
+| 0.5352        | 2.0   | 20   | 0.5909          | 0.7      |
+| 0.4461        | 3.0   | 30   | 0.5032          | 0.8      |
+| 0.3148        | 4.0   | 40   | 0.4405          | 0.8      |
+| 0.2678        | 5.0   | 50   | 0.4231          | 0.8      |
 
 
 ### Framework versions