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 [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2158
-- F1: 0.9434
+- Loss: 1.0133
+- F1: 0.5792
 
 ## Model description
 
@@ -43,21 +43,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
-- num_epochs: 10
+- num_epochs: 12
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.1707        | 1.18  | 100  | 0.9760          | 0.3479 |
-| 0.9249        | 2.35  | 200  | 0.7532          | 0.6489 |
-| 0.7754        | 3.53  | 300  | 0.6164          | 0.7569 |
-| 0.628         | 4.71  | 400  | 0.5036          | 0.8118 |
-| 0.5537        | 5.88  | 500  | 0.3762          | 0.8734 |
-| 0.451         | 7.06  | 600  | 0.3100          | 0.8990 |
-| 0.3917        | 8.24  | 700  | 0.2503          | 0.9263 |
-| 0.3416        | 9.41  | 800  | 0.2158          | 0.9434 |
+| 1.169         | 1.18  | 100  | 1.0580          | 0.2159 |
+| 0.9143        | 2.35  | 200  | 0.9283          | 0.5405 |
+| 0.7535        | 3.53  | 300  | 0.9387          | 0.5665 |
+| 0.6085        | 4.71  | 400  | 0.9574          | 0.5664 |
+| 0.53          | 5.88  | 500  | 1.0133          | 0.5792 |
 
 
 ### Framework versions