End of training

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9737511445721844
+      value: 0.9608762098828324
     - name: Recall
       type: recall
-      value: 0.974544343753182
+      value: 0.9602891762549639
     - name: F1
       type: f1
-      value: 0.974147582697201
+      value: 0.9605826033815442
     - name: Accuracy
       type: accuracy
-      value: 0.9767916100213634
+      value: 0.9654301806175957
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cis-lmu/glot500-base](https://huggingface.co/cis-lmu/glot500-base) on the universal_dependencies dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0882
-- Precision: 0.9738
-- Recall: 0.9745
-- F1: 0.9741
-- Accuracy: 0.9768
+- Loss: 0.1267
+- Precision: 0.9609
+- Recall: 0.9603
+- F1: 0.9606
+- Accuracy: 0.9654
 
 ## Model description
 
@@ -80,8 +80,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.7975        | 1.0   | 904  | 0.1091          | 0.9679    | 0.9673 | 0.9676 | 0.9711   |
-| 0.0735        | 2.0   | 1808 | 0.0882          | 0.9738    | 0.9745 | 0.9741 | 0.9768   |
+| 0.9175        | 1.0   | 904  | 0.1582          | 0.9548    | 0.9541 | 0.9544 | 0.9601   |
+| 0.1162        | 2.0   | 1808 | 0.1267          | 0.9609    | 0.9603 | 0.9606 | 0.9654   |
 
 
 ### Framework versions