update model card README.md

README.md

@@ -15,13 +15,13 @@ model-index:
     dataset:
       name: xtreme
       type: xtreme
-      config: PAN-X.de
+      config: PAN-X.zh
       split: validation
-      args: PAN-X.de
+      args: PAN-X.zh
     metrics:
     - name: F1
       type: f1
-      value: 0.8609120891618334
+      value: 0.7524781627245068
 ---
 
 <!-- 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: 0.1400
-- F1: 0.8609
+- Loss: 0.2188
+- F1: 0.7525
 
 ## Model description
 
@@ -63,14 +63,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.2581        | 1.0   | 525  | 0.1584          | 0.8233 |
-| 0.1252        | 2.0   | 1050 | 0.1384          | 0.8491 |
-| 0.0811        | 3.0   | 1575 | 0.1400          | 0.8609 |
+| 0.3742        | 1.0   | 667  | 0.2543          | 0.6753 |
+| 0.2248        | 2.0   | 1334 | 0.2185          | 0.7343 |
+| 0.1606        | 3.0   | 2001 | 0.2188          | 0.7525 |
 
 
 ### Framework versions
 
-- Transformers 4.27.4
+- Transformers 4.28.1
 - Pytorch 2.0.0+cu118
 - Datasets 2.11.0
 - Tokenizers 0.13.3