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: 3.3049
+- Loss: 3.3043
 
 ## Model description
 
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.5548        | 1.0   | 157  | 3.3250          |
-| 3.4067        | 2.0   | 314  | 3.2857          |
-| 3.37          | 3.0   | 471  | 3.2793          |
+| 3.5536        | 1.0   | 157  | 3.3242          |
+| 3.4026        | 2.0   | 314  | 3.2848          |
+| 3.3708        | 3.0   | 471  | 3.2791          |
 
 
 ### Framework versions
 
 - Transformers 4.16.0.dev0
 - Pytorch 1.10.0
-- Datasets 1.16.2.dev0
+- Datasets 1.17.1.dev0
 - Tokenizers 0.10.3