Training complete

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.7789745315830809
+      value: 0.7830405270513077
     - name: Recall
       type: recall
-      value: 0.7834869287192026
+      value: 0.7856186076789224
     - name: F1
       type: f1
-      value: 0.7812242142374916
+      value: 0.7843274488361194
     - name: Accuracy
       type: accuracy
-      value: 0.8373975143936409
+      value: 0.8402036064122549
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mHossain/bengali_pos_v1_300000](https://huggingface.co/mHossain/bengali_pos_v1_300000) on the pos_tag_100k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8124
-- Precision: 0.7790
-- Recall: 0.7835
-- F1: 0.7812
-- Accuracy: 0.8374
+- Loss: 0.5609
+- Precision: 0.7830
+- Recall: 0.7856
+- F1: 0.7843
+- Accuracy: 0.8402
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1734        | 1.0   | 22500 | 0.8216          | 0.7712    | 0.7729 | 0.7721 | 0.8311   |
-| 0.1675        | 2.0   | 45000 | 0.8596          | 0.7765    | 0.7799 | 0.7782 | 0.8347   |
-| 0.2639        | 3.0   | 67500 | 0.8124          | 0.7790    | 0.7835 | 0.7812 | 0.8374   |
+| 0.5908        | 1.0   | 22500 | 0.5513          | 0.7688    | 0.7698 | 0.7693 | 0.8289   |
+| 0.4642        | 2.0   | 45000 | 0.5415          | 0.7799    | 0.7822 | 0.7810 | 0.8382   |
+| 0.3773        | 3.0   | 67500 | 0.5609          | 0.7830    | 0.7856 | 0.7843 | 0.8402   |
 
 
 ### Framework versions