update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bigcode/starencoder](https://huggingface.co/bigcode/starencoder) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9191
-- Accuracy: 0.89
+- Loss: 0.4538
+- Accuracy: 0.875
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 7    | 0.9695          | 0.89     |
-| 0.9787        | 2.0   | 14   | 0.9507          | 0.89     |
-| 0.9456        | 3.0   | 21   | 0.9191          | 0.89     |
+| 0.3098        | 1.0   | 1485 | 0.3670          | 0.89     |
+| 0.4251        | 2.0   | 2970 | 0.3698          | 0.88     |
+| 0.226         | 3.0   | 4455 | 0.4538          | 0.875    |
 
 
 ### Framework versions