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: 0.5246
-- Accuracy: 0.8
+- Loss: 0.5507
+- Accuracy: 0.8857
 
 ## Model description
 
@@ -43,14 +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: 2
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 18   | 0.6145          | 0.6857   |
-| No log        | 2.0   | 36   | 0.5246          | 0.8      |
+| No log        | 1.0   | 18   | 0.5782          | 0.7714   |
+| No log        | 2.0   | 36   | 0.4217          | 0.8      |
+| No log        | 3.0   | 54   | 0.4752          | 0.8286   |
+| No log        | 4.0   | 72   | 0.3928          | 0.8857   |
+| No log        | 5.0   | 90   | 0.6735          | 0.7714   |
+| No log        | 6.0   | 108  | 0.4541          | 0.8857   |
+| No log        | 7.0   | 126  | 0.5278          | 0.8857   |
+| No log        | 8.0   | 144  | 0.5449          | 0.8857   |
+| No log        | 9.0   | 162  | 0.5482          | 0.8857   |
+| No log        | 10.0  | 180  | 0.5507          | 0.8857   |
 
 
 ### Framework versions