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: 2.4734
+- Loss: 2.4721
 
 ## Model description
 
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.7117        | 1.0   | 157  | 2.4976          |
-| 2.5773        | 2.0   | 314  | 2.4243          |
-| 2.5263        | 3.0   | 471  | 2.4348          |
+| 2.7086        | 1.0   | 157  | 2.4898          |
+| 2.5796        | 2.0   | 314  | 2.4230          |
+| 2.5269        | 3.0   | 471  | 2.4354          |
 
 
 ### Framework versions
 
-- Transformers 4.19.2
-- Pytorch 1.11.0+cu113
-- Datasets 2.2.1
+- Transformers 4.22.1
+- Pytorch 1.12.1+cu113
+- Datasets 2.5.1
 - Tokenizers 0.12.1