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 [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6420
+- Loss: 3.6417
 
 ## Model description
 
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.7559        | 1.0   | 2334 | 3.6646          |
-| 3.6393        | 2.0   | 4668 | 3.6482          |
-| 3.5939        | 3.0   | 7002 | 3.6420          |
+| 3.7557        | 1.0   | 2334 | 3.6642          |
+| 3.6392        | 2.0   | 4668 | 3.6480          |
+| 3.5938        | 3.0   | 7002 | 3.6417          |
 
 
 ### Framework versions
 
-- Transformers 4.33.0.dev0
+- Transformers 4.31.0
 - Pytorch 2.1.0a0+b5021ba
 - Datasets 2.14.4
 - Tokenizers 0.13.3