update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2350
-- Accuracy: 0.9308
+- Loss: 0.5520
+- Accuracy: 0.8991
 
 ## Model description
 
@@ -41,22 +41,17 @@ 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: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 67   | 0.1916          | 0.9271   |
-| 0.2043        | 2.0   | 134  | 0.1966          | 0.9290   |
-| 0.2043        | 3.0   | 201  | 0.2103          | 0.9252   |
-| 0.1106        | 4.0   | 268  | 0.2124          | 0.9308   |
-| 0.1106        | 5.0   | 335  | 0.2114          | 0.9290   |
-| 0.0694        | 6.0   | 402  | 0.2184          | 0.9271   |
-| 0.0694        | 7.0   | 469  | 0.2300          | 0.9327   |
-| 0.0391        | 8.0   | 536  | 0.2332          | 0.9252   |
-| 0.0391        | 9.0   | 603  | 0.2351          | 0.9308   |
-| 0.0392        | 10.0  | 670  | 0.2350          | 0.9308   |
+| No log        | 1.0   | 67   | 0.5258          | 0.8935   |
+| 0.0073        | 2.0   | 134  | 0.5262          | 0.8972   |
+| 0.0073        | 3.0   | 201  | 0.5408          | 0.8972   |
+| 0.0053        | 4.0   | 268  | 0.5494          | 0.8991   |
+| 0.0053        | 5.0   | 335  | 0.5520          | 0.8991   |
 
 
 ### Framework versions