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: 0.2192
-- Accuracy: 0.9265
-- F1: 0.9264
+- Loss: 0.1491
+- Accuracy: 0.939
+- F1: 0.9390
 
 ## Model description
 
@@ -44,14 +44,15 @@ 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: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8829        | 1.0   | 250  | 0.3189          | 0.9125   | 0.9102 |
-| 0.2566        | 2.0   | 500  | 0.2192          | 0.9265   | 0.9264 |
+| 0.1789        | 1.0   | 250  | 0.1740          | 0.932    | 0.9314 |
+| 0.1189        | 2.0   | 500  | 0.1573          | 0.936    | 0.9361 |
+| 0.098         | 3.0   | 750  | 0.1491          | 0.939    | 0.9390 |
 
 
 ### Framework versions