update model card README.md

README.md

@@ -18,9 +18,9 @@ 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: 0.2216
-- Accuracy: 0.921
-- F1: 0.9209
+- Loss: 0.1803
+- Accuracy: 0.94
+- F1: 0.9400
 
 ## Model description
 
@@ -45,14 +45,22 @@ 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: 2
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8575        | 1.0   | 250  | 0.3283          | 0.905    | 0.9042 |
-| 0.262         | 2.0   | 500  | 0.2216          | 0.921    | 0.9209 |
+| 0.5017        | 1.0   | 250  | 0.2116          | 0.9295   | 0.9305 |
+| 0.1763        | 2.0   | 500  | 0.1617          | 0.936    | 0.9369 |
+| 0.1267        | 3.0   | 750  | 0.1492          | 0.9385   | 0.9386 |
+| 0.0979        | 4.0   | 1000 | 0.1495          | 0.9395   | 0.9392 |
+| 0.0787        | 5.0   | 1250 | 0.1602          | 0.935    | 0.9349 |
+| 0.067         | 6.0   | 1500 | 0.1588          | 0.9405   | 0.9401 |
+| 0.0557        | 7.0   | 1750 | 0.1675          | 0.9415   | 0.9413 |
+| 0.0452        | 8.0   | 2000 | 0.1764          | 0.937    | 0.9365 |
+| 0.0375        | 9.0   | 2250 | 0.1765          | 0.9405   | 0.9406 |
+| 0.0337        | 10.0  | 2500 | 0.1803          | 0.94     | 0.9400 |
 
 
 ### Framework versions