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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6497
-- Precision: 0.1818
-- Recall: 0.2
-- F1: 0.1905
-- Accuracy: 0.5093
+- Loss: 0.9988
+- Precision: 0.3
+- Recall: 0.6
+- F1: 0.4
+- Accuracy: 0.7870
 
 ## 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   | 19   | 1.3083          | 0.0       | 0.0    | 0.0    | 0.3981   |
-| No log        | 2.0   | 38   | 1.5496          | 0.2222    | 0.2    | 0.2105 | 0.4907   |
-| No log        | 3.0   | 57   | 1.6497          | 0.1818    | 0.2    | 0.1905 | 0.5093   |
+| No log        | 1.0   | 84   | 0.8399          | 0.2105    | 0.4    | 0.2759 | 0.75     |
+| No log        | 2.0   | 168  | 0.9664          | 0.3       | 0.6    | 0.4    | 0.7870   |
+| No log        | 3.0   | 252  | 0.9988          | 0.3       | 0.6    | 0.4    | 0.7870   |
 
 
 ### Framework versions
 
-- Transformers 4.16.1
+- Transformers 4.16.2
 - Pytorch 1.10.0+cu111
 - Datasets 1.18.2
 - Tokenizers 0.11.0