update model card README.md

README.md

@@ -17,9 +17,9 @@ 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: 0.5606
-- Accuracy: 0.843
-- F1: 0.8279
+- Loss: 0.4542
+- Accuracy: 0.869
+- F1: 0.8626
 
 ## Model description
 
@@ -44,18 +44,22 @@ 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: 6
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 2.274         | 1.0   | 110  | 1.4271          | 0.667    | 0.6097 |
-| 1.16          | 2.0   | 220  | 0.8743          | 0.791    | 0.7584 |
-| 0.7726        | 3.0   | 330  | 0.6892          | 0.815    | 0.7922 |
-| 0.6116        | 4.0   | 440  | 0.6138          | 0.831    | 0.8151 |
-| 0.5204        | 5.0   | 550  | 0.5680          | 0.842    | 0.8261 |
-| 0.4756        | 6.0   | 660  | 0.5606          | 0.843    | 0.8279 |
+| 2.2847        | 1.0   | 110  | 1.3868          | 0.681    | 0.6215 |
+| 1.1164        | 2.0   | 220  | 0.8190          | 0.804    | 0.7759 |
+| 0.7155        | 3.0   | 330  | 0.6261          | 0.833    | 0.8127 |
+| 0.5457        | 4.0   | 440  | 0.5272          | 0.859    | 0.8464 |
+| 0.4425        | 5.0   | 550  | 0.4858          | 0.868    | 0.8586 |
+| 0.3716        | 6.0   | 660  | 0.4751          | 0.868    | 0.8606 |
+| 0.3212        | 7.0   | 770  | 0.4630          | 0.865    | 0.8573 |
+| 0.2819        | 8.0   | 880  | 0.4587          | 0.874    | 0.8681 |
+| 0.2709        | 9.0   | 990  | 0.4538          | 0.874    | 0.8676 |
+| 0.2375        | 10.0  | 1100 | 0.4542          | 0.869    | 0.8626 |
 
 
 ### Framework versions