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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2299
-- F1: 0.3335
+- Loss: 0.9256
+- F1: 0.4541
 
 ## Model description
 
@@ -43,15 +43,21 @@ 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: 8
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.8627        | 3.53  | 300  | 1.4982          | 0.2206 |
-| 1.4171        | 7.06  | 600  | 1.2299          | 0.3335 |
+| 2.1225        | 1.18  | 100  | 1.8712          | 0.1078 |
+| 1.7933        | 2.35  | 200  | 1.6171          | 0.1861 |
+| 1.5819        | 3.53  | 300  | 1.4004          | 0.2706 |
+| 1.4077        | 4.71  | 400  | 1.2577          | 0.2964 |
+| 1.2928        | 5.88  | 500  | 1.1136          | 0.3732 |
+| 1.182         | 7.06  | 600  | 1.0234          | 0.4052 |
+| 1.1092        | 8.24  | 700  | 0.9653          | 0.4457 |
+| 1.052         | 9.41  | 800  | 0.9256          | 0.4541 |
 
 
 ### Framework versions