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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1473
-- Accuracy: 0.6490
-- F1: 0.6490
+- Loss: 0.8186
+- Accuracy: 0.6630
+- F1: 0.6630
 
 ## Model description
 
@@ -44,17 +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: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.7569        | 1.0   | 1839 | 0.7595          | 0.6631   | 0.6631 |
-| 0.6716        | 2.0   | 3678 | 0.7809          | 0.6589   | 0.6589 |
-| 0.527         | 3.0   | 5517 | 0.8484          | 0.6619   | 0.6619 |
-| 0.3963        | 4.0   | 7356 | 1.0179          | 0.6486   | 0.6486 |
-| 0.296         | 5.0   | 9195 | 1.1473          | 0.6490   | 0.6490 |
+| 0.7581        | 1.0   | 1839 | 0.7575          | 0.6649   | 0.6649 |
+| 0.6685        | 2.0   | 3678 | 0.7727          | 0.6611   | 0.6611 |
+| 0.5403        | 3.0   | 5517 | 0.8186          | 0.6630   | 0.6630 |
 
 
 ### Framework versions