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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1691
-- Accuracy: 0.95
+- Loss: 0.2224
+- Accuracy: 0.925
 
 ## Model description
 
@@ -43,17 +43,22 @@ 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: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 0.5176          | 0.9      |
-| No log        | 2.0   | 80   | 0.2608          | 0.95     |
-| No log        | 3.0   | 120  | 0.1952          | 0.95     |
-| No log        | 4.0   | 160  | 0.2373          | 0.9      |
-| No log        | 5.0   | 200  | 0.1691          | 0.95     |
+| No log        | 1.0   | 40   | 0.5824          | 0.575    |
+| No log        | 2.0   | 80   | 0.3768          | 0.95     |
+| No log        | 3.0   | 120  | 0.2381          | 0.925    |
+| No log        | 4.0   | 160  | 0.2721          | 0.9      |
+| No log        | 5.0   | 200  | 0.1597          | 0.95     |
+| No log        | 6.0   | 240  | 0.2096          | 0.95     |
+| No log        | 7.0   | 280  | 0.4053          | 0.825    |
+| No log        | 8.0   | 320  | 0.2440          | 0.9      |
+| No log        | 9.0   | 360  | 0.2514          | 0.9      |
+| No log        | 10.0  | 400  | 0.2224          | 0.925    |
 
 
 ### Framework versions