update model card README.md

README.md

@@ -17,8 +17,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2614
-- Accuracy: 0.9296
+- Loss: 0.0942
+- Accuracy: 0.9799
 
 ## Model description
 
@@ -43,14 +43,17 @@ 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: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 112  | 0.2497          | 0.9246   |
-| No log        | 2.0   | 224  | 0.2614          | 0.9296   |
+| No log        | 1.0   | 112  | 0.1198          | 0.9749   |
+| No log        | 2.0   | 224  | 0.0874          | 0.9698   |
+| No log        | 3.0   | 336  | 0.1638          | 0.9598   |
+| No log        | 4.0   | 448  | 0.1002          | 0.9799   |
+| 0.1595        | 5.0   | 560  | 0.0942          | 0.9799   |
 
 
 ### Framework versions