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-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8874
-- F1: 0.4567
+- Loss: 1.6113
+- F1: 0.2785
 
 ## Model description
 
@@ -43,21 +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: 10
+- num_epochs: 12
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 2.0846        | 1.18  | 100  | 1.7960          | 0.1332 |
-| 1.7183        | 2.35  | 200  | 1.5586          | 0.2069 |
-| 1.528         | 3.53  | 300  | 1.3556          | 0.2878 |
-| 1.3757        | 4.71  | 400  | 1.2125          | 0.3072 |
-| 1.2765        | 5.88  | 500  | 1.0967          | 0.3505 |
-| 1.1601        | 7.06  | 600  | 0.9844          | 0.4100 |
-| 1.0878        | 8.24  | 700  | 0.9205          | 0.4360 |
-| 1.0269        | 9.41  | 800  | 0.8874          | 0.4567 |
+| 2.0125        | 1.18  | 100  | 1.8290          | 0.1089 |
+| 1.6698        | 2.35  | 200  | 1.6458          | 0.2223 |
+| 1.4812        | 3.53  | 300  | 1.6035          | 0.2463 |
+| 1.3137        | 4.71  | 400  | 1.5729          | 0.2502 |
+| 1.2143        | 5.88  | 500  | 1.5549          | 0.2697 |
+| 1.0805        | 7.06  | 600  | 1.5553          | 0.2759 |
+| 0.9838        | 8.24  | 700  | 1.5730          | 0.2879 |
+| 0.8981        | 9.41  | 800  | 1.6113          | 0.2785 |
 
 
 ### Framework versions