update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [augustocsc/gpt-m](https://huggingface.co/augustocsc/gpt-m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0017
+- Loss: 0.0023
 
 ## Model description
 
@@ -45,16 +45,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0065        | 0.55  | 500  | 0.0027          |
-| 0.0086        | 1.1   | 1000 | 0.0020          |
-| 0.0023        | 1.65  | 1500 | 0.0020          |
-| 0.002         | 2.2   | 2000 | 0.0019          |
-| 0.0021        | 2.75  | 2500 | 0.0018          |
-| 0.0021        | 3.3   | 3000 | 0.0019          |
-| 0.002         | 3.85  | 3500 | 0.0017          |
-| 0.0019        | 4.4   | 4000 | 0.0018          |
-| 0.002         | 4.95  | 4500 | 0.0017          |
-| 0.0019        | 5.5   | 5000 | 0.0017          |
+| 0.0053        | 0.55  | 500  | 0.0030          |
+| 0.0034        | 1.1   | 1000 | 0.0029          |
+| 0.0027        | 1.65  | 1500 | 0.0034          |
+| 0.0027        | 2.2   | 2000 | 0.0026          |
+| 0.0027        | 2.75  | 2500 | 0.0024          |
+| 0.0027        | 3.3   | 3000 | 0.0024          |
+| 0.0026        | 3.85  | 3500 | 0.0023          |
+| 0.0024        | 4.4   | 4000 | 0.0024          |
+| 0.0024        | 4.95  | 4500 | 0.0023          |
+| 0.0025        | 5.5   | 5000 | 0.0023          |
 
 
 ### Framework versions