update model card README.md

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4726
+- Loss: 0.6624
 
 ## Model description
 
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.709         | 1.0   | 157  | 2.4959          |
-| 2.5772        | 2.0   | 314  | 2.4247          |
-| 2.5408        | 3.0   | 471  | 2.4356          |
+| 0.7603        | 1.0   | 157  | 0.6641          |
+| 0.6866        | 2.0   | 314  | 0.6578          |
+| 0.6793        | 3.0   | 471  | 0.6606          |
 
 
 ### Framework versions
 
-- Transformers 4.13.0.dev0
+- Transformers 4.16.0.dev0
 - Pytorch 1.10.0
 - Datasets 1.16.2.dev0
 - Tokenizers 0.10.3