update model card README.md

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 13.0832
+- Loss: 4.3328
 
 ## Model description
 
@@ -40,14 +40,32 @@ 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: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 6    | 13.5907         |
-| No log        | 2.0   | 12   | 13.0832         |
+| No log        | 1.0   | 6    | 13.2699         |
+| No log        | 2.0   | 12   | 12.2786         |
+| No log        | 3.0   | 18   | 11.5745         |
+| No log        | 4.0   | 24   | 10.8457         |
+| No log        | 5.0   | 30   | 9.8424          |
+| No log        | 6.0   | 36   | 8.5779          |
+| No log        | 7.0   | 42   | 6.9630          |
+| No log        | 8.0   | 48   | 6.1362          |
+| No log        | 9.0   | 54   | 5.6167          |
+| No log        | 10.0  | 60   | 5.3033          |
+| No log        | 11.0  | 66   | 5.0873          |
+| No log        | 12.0  | 72   | 4.8782          |
+| No log        | 13.0  | 78   | 4.7162          |
+| No log        | 14.0  | 84   | 4.6101          |
+| No log        | 15.0  | 90   | 4.5256          |
+| No log        | 16.0  | 96   | 4.4572          |
+| No log        | 17.0  | 102  | 4.4019          |
+| No log        | 18.0  | 108  | 4.3624          |
+| No log        | 19.0  | 114  | 4.3405          |
+| No log        | 20.0  | 120  | 4.3328          |
 
 
 ### Framework versions