Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8954509177972865
+      value: 0.9014463504877228
     - name: Recall
       type: recall
-      value: 0.8834645669291339
+      value: 0.9038785834738617
     - name: F1
       type: f1
-      value: 0.8894173602853745
+      value: 0.9026608285618053
     - name: Accuracy
       type: accuracy
-      value: 0.9820464165815209
+      value: 0.9895516717325228
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ 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 id_nergrit_corpus dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0942
-- Precision: 0.8955
-- Recall: 0.8835
-- F1: 0.8894
-- Accuracy: 0.9820
+- Loss: 0.0457
+- Precision: 0.9014
+- Recall: 0.9039
+- F1: 0.9027
+- Accuracy: 0.9896
 
 ## Model description
 
@@ -67,8 +67,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 2
+- learning_rate: 5e-05
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0955        | 1.0   | 2285 | 0.0766          | 0.8528    | 0.8669 | 0.8598 | 0.9813   |
-| 0.0558        | 2.0   | 4570 | 0.0860          | 0.8867    | 0.8693 | 0.8779 | 0.9811   |
-| 0.0368        | 3.0   | 6855 | 0.0942          | 0.8955    | 0.8835 | 0.8894 | 0.9820   |
+| 0.0492        | 1.0   | 1567 | 0.0410          | 0.8863    | 0.8938 | 0.8900 | 0.9886   |
+| 0.0285        | 2.0   | 3134 | 0.0416          | 0.8941    | 0.9025 | 0.8983 | 0.9895   |
+| 0.0159        | 3.0   | 4701 | 0.0457          | 0.9014    | 0.9039 | 0.9027 | 0.9896   |
 
 
 ### Framework versions