update model card README.md

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base](https://huggingface.co/cardiffnlp/twitter-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3931
-- Precision: 0.8809
-- Recall: 0.9501
-- F1: 0.9142
-- Accuracy: 0.8579
+- Loss: 0.4936
+- Precision: 0.8189
+- Recall: 0.9811
+- F1: 0.8927
+- Accuracy: 0.8120
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 130  | 0.4105          | 0.8568    | 0.9645 | 0.9075 | 0.8438   |
-| No log        | 2.0   | 260  | 0.4006          | 0.8520    | 0.9754 | 0.9096 | 0.8460   |
-| No log        | 3.0   | 390  | 0.4112          | 0.8543    | 0.9454 | 0.8975 | 0.8286   |
-| 0.376         | 4.0   | 520  | 0.4278          | 0.8711    | 0.9235 | 0.8966 | 0.8308   |
-| 0.376         | 5.0   | 650  | 0.4430          | 0.8655    | 0.9317 | 0.8974 | 0.8308   |
+| No log        | 1.0   | 13   | 0.5150          | 0.7447    | 1.0    | 0.8537 | 0.7447   |
+| No log        | 2.0   | 26   | 0.5565          | 0.7447    | 1.0    | 0.8537 | 0.7447   |
+| No log        | 3.0   | 39   | 0.5438          | 0.7778    | 1.0    | 0.8750 | 0.7872   |
+| No log        | 4.0   | 52   | 0.5495          | 0.7778    | 1.0    | 0.8750 | 0.7872   |
+| No log        | 5.0   | 65   | 0.5936          | 0.7778    | 1.0    | 0.8750 | 0.7872   |
 
 
 ### Framework versions