Fine-tuned mBERT for Urdu sentiment classification — corrected labels

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8915
-- Accuracy: 0.81
-- F1: 0.8098
+- Loss: 1.0358
+- Accuracy: 0.8074
+- F1: 0.8073
 
 ## Model description
 
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8954        | 1.0   | 625  | 0.9527          | 0.7696   | 0.7656 |
-| 0.7918        | 2.0   | 1250 | 0.8385          | 0.8      | 0.7999 |
-| 0.6211        | 3.0   | 1875 | 0.8908          | 0.8101   | 0.8099 |
-| 0.5833        | 4.0   | 2500 | 0.9350          | 0.8088   | 0.8087 |
-| 0.4515        | 5.0   | 3125 | 1.0381          | 0.8081   | 0.8081 |
+| 0.8904        | 1.0   | 625  | 0.9830          | 0.7664   | 0.7622 |
+| 0.7935        | 2.0   | 1250 | 0.8413          | 0.7978   | 0.7975 |
+| 0.6253        | 3.0   | 1875 | 0.9115          | 0.8021   | 0.8014 |
+| 0.5877        | 4.0   | 2500 | 0.9304          | 0.8055   | 0.8051 |
+| 0.4309        | 5.0   | 3125 | 1.0358          | 0.8074   | 0.8073 |
 
 
 ### Framework versions