update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0210
-- Precision: 0.8694
-- Recall: 0.8778
-- F1: 0.8736
-- Accuracy: 0.9942
+- Loss: 0.0176
+- Precision: 0.8418
+- Recall: 0.8095
+- F1: 0.8253
+- Accuracy: 0.9937
 
 ## Model description
 
@@ -54,14 +54,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 54   | 0.0310          | 0.7669    | 0.8039 | 0.7849 | 0.9916   |
-| No log        | 2.0   | 108  | 0.0229          | 0.8571    | 0.8103 | 0.8331 | 0.9931   |
-| No log        | 3.0   | 162  | 0.0210          | 0.8694    | 0.8778 | 0.8736 | 0.9942   |
+| No log        | 1.0   | 48   | 0.0268          | 0.7280    | 0.7829 | 0.7544 | 0.9908   |
+| No log        | 2.0   | 96   | 0.0194          | 0.8295    | 0.8050 | 0.8171 | 0.9934   |
+| No log        | 3.0   | 144  | 0.0176          | 0.8418    | 0.8095 | 0.8253 | 0.9937   |
 
 
 ### Framework versions
 
-- Transformers 4.11.3
-- Pytorch 1.10.0+cu111
-- Datasets 1.16.1
-- Tokenizers 0.10.3
+- Transformers 4.18.0
+- Pytorch 1.11.0
+- Datasets 2.1.0
+- Tokenizers 0.12.1