update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.9471218206157965
+      value: 0.9525165396532953
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0364
-- F1: 0.9471
+- Loss: 0.0409
+- F1: 0.9525
 
 ## Model description
 
@@ -52,20 +52,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 24
-- eval_batch_size: 24
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.128         | 1.0   | 586  | 0.0458          | 0.9310 |
-| 0.0355        | 2.0   | 1172 | 0.0376          | 0.9426 |
-| 0.0176        | 3.0   | 1758 | 0.0364          | 0.9471 |
+| 0.1394        | 1.0   | 439  | 0.0482          | 0.9274 |
+| 0.0399        | 2.0   | 878  | 0.0393          | 0.9407 |
+| 0.0221        | 3.0   | 1317 | 0.0357          | 0.9488 |
+| 0.013         | 4.0   | 1756 | 0.0355          | 0.9518 |
+| 0.0077        | 5.0   | 2195 | 0.0404          | 0.9524 |
+| 0.0046        | 6.0   | 2634 | 0.0409          | 0.9525 |
 
 
 ### Framework versions