update model card README.md

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the swag dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4995
-- Accuracy: 0.8303
+- Loss: 0.4753
+- Accuracy: 0.8242
 
 ## Model description
 
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0188        | 1.0   | 2298 | 0.5664          | 0.7779   |
-| 0.2376        | 2.0   | 4596 | 0.4749          | 0.8192   |
-| 0.2322        | 3.0   | 6894 | 0.4995          | 0.8303   |
+| 1.45          | 1.0   | 2298 | 1.3857          | 0.4485   |
+| 0.3628        | 2.0   | 4596 | 0.4802          | 0.8163   |
+| 0.1821        | 3.0   | 6894 | 0.4753          | 0.8242   |
 
 
 ### Framework versions
 
 - Transformers 4.20.1
 - Pytorch 1.10.0+cpu
-- Datasets 2.7.0
+- Datasets 2.7.1
 - Tokenizers 0.12.1