update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6979
-- Accuracy: 0.8667
+- Loss: 0.6174
+- Accuracy: 0.6667
 
 ## Model description
 
@@ -36,28 +36,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
+- learning_rate: 6.426351850922471e-05
+- train_batch_size: 16
 - eval_batch_size: 8
-- seed: 42
+- seed: 31
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7455        | 1.0   | 15   | 0.5145          | 0.7333   |
-| 0.3538        | 2.0   | 30   | 0.5529          | 0.7333   |
-| 0.1785        | 3.0   | 45   | 0.6121          | 0.8      |
-| 0.0672        | 4.0   | 60   | 0.6731          | 0.8667   |
-| 0.0508        | 5.0   | 75   | 0.6979          | 0.8667   |
+| 0.9335        | 1.0   | 8    | 0.7771          | 0.5333   |
+| 0.5801        | 2.0   | 16   | 0.6174          | 0.6667   |
 
 
 ### Framework versions
 
 - Transformers 4.31.0
 - Pytorch 2.0.1
-- Datasets 2.14.0
+- Datasets 2.14.1
 - Tokenizers 0.13.3