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 [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.7297
+- Loss: 3.7487
 
 ## Model description
 
@@ -45,14 +45,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.8665        | 1.0   | 1124 | 3.7511          |
-| 3.7758        | 2.0   | 2248 | 3.7323          |
-| 3.7306        | 3.0   | 3372 | 3.7297          |
+| 3.8656        | 1.0   | 1115 | 3.7672          |
+| 3.7775        | 2.0   | 2230 | 3.7529          |
+| 3.7321        | 3.0   | 3345 | 3.7487          |
 
 
 ### Framework versions
 
-- Transformers 4.29.1
+- Transformers 4.29.2
 - Pytorch 1.12.1
 - Datasets 2.11.0
 - Tokenizers 0.11.0