update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.8703271692745377
+      value: 0.8381502890173411
 ---
 
 <!-- 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 xtreme dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1422
-- F1: 0.8703
+- Loss: 0.1557
+- F1: 0.8382
 
 ## Model description
 
@@ -51,9 +51,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 24
-- eval_batch_size: 24
+- learning_rate: 5e-06
+- train_batch_size: 12
+- eval_batch_size: 12
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -63,10 +63,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.2598        | 1.0   | 525  | 0.1673          | 0.8109 |
-| 0.1323        | 2.0   | 1050 | 0.1439          | 0.8495 |
-| 0.0873        | 3.0   | 1575 | 0.1434          | 0.8594 |
-| 0.0572        | 4.0   | 2100 | 0.1422          | 0.8703 |
+| 0.3792        | 1.0   | 1049 | 0.1883          | 0.8082 |
+| 0.1873        | 2.0   | 2098 | 0.1652          | 0.8295 |
+| 0.1568        | 3.0   | 3147 | 0.1577          | 0.8317 |
+| 0.1439        | 4.0   | 4196 | 0.1557          | 0.8382 |
 
 
 ### Framework versions