update model card README.md

README.md

@@ -17,9 +17,9 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4984
-- Accuracy: 0.77
-- F1: 0.7699
+- Loss: 0.4660
+- Accuracy: 0.87
+- F1: 0.8697
 
 ## Model description
 
@@ -38,22 +38,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8.385087187335001e-05
+- learning_rate: 9.910294163459086e-05
 - train_batch_size: 400
 - eval_batch_size: 400
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 9
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 5    | 0.6611          | 0.57     | 0.5575 |
-| No log        | 2.0   | 10   | 0.5364          | 0.74     | 0.7397 |
-| No log        | 3.0   | 15   | 0.5210          | 0.76     | 0.7586 |
-| No log        | 4.0   | 20   | 0.4984          | 0.77     | 0.7699 |
+| No log        | 1.0   | 5    | 0.6509          | 0.59     | 0.5780 |
+| No log        | 2.0   | 10   | 0.4950          | 0.77     | 0.7701 |
+| No log        | 3.0   | 15   | 0.4787          | 0.81     | 0.8099 |
+| No log        | 4.0   | 20   | 0.4936          | 0.81     | 0.8096 |
+| No log        | 5.0   | 25   | 0.4443          | 0.82     | 0.82   |
+| No log        | 6.0   | 30   | 0.4547          | 0.85     | 0.8497 |
+| No log        | 7.0   | 35   | 0.4268          | 0.85     | 0.8500 |
+| No log        | 8.0   | 40   | 0.4790          | 0.87     | 0.8697 |
+| No log        | 9.0   | 45   | 0.4660          | 0.87     | 0.8697 |
 
 
 ### Framework versions