Model save

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8265817023213473
+      value: 0.8359161349134002
     - name: Recall
       type: recall
-      value: 0.8764478764478765
+      value: 0.8851351351351351
     - name: F1
       type: f1
-      value: 0.850784727102366
+      value: 0.8598218471636193
     - name: Accuracy
       type: accuracy
-      value: 0.9683326090105752
+      value: 0.9700420107199769
 ---
 
 <!-- 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 [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1794
-- Precision: 0.8266
-- Recall: 0.8764
-- F1: 0.8508
-- Accuracy: 0.9683
+- Loss: 0.1918
+- Precision: 0.8359
+- Recall: 0.8851
+- F1: 0.8598
+- Accuracy: 0.9700
 
 ## Model description
 
@@ -73,18 +73,21 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2748        | 2.22  | 500  | 0.1464          | 0.7658    | 0.8364 | 0.7995 | 0.9622   |
-| 0.0997        | 4.44  | 1000 | 0.1377          | 0.7822    | 0.8716 | 0.8245 | 0.9653   |
-| 0.0677        | 6.67  | 1500 | 0.1525          | 0.7997    | 0.8769 | 0.8366 | 0.9657   |
-| 0.0452        | 8.89  | 2000 | 0.1426          | 0.8162    | 0.8832 | 0.8484 | 0.9698   |
-| 0.0316        | 11.11 | 2500 | 0.1737          | 0.8232    | 0.8697 | 0.8458 | 0.9683   |
-| 0.023         | 13.33 | 3000 | 0.1794          | 0.8266    | 0.8764 | 0.8508 | 0.9683   |
+| 0.2903        | 2.22  | 500  | 0.1438          | 0.7586    | 0.8417 | 0.7980 | 0.9626   |
+| 0.1147        | 4.44  | 1000 | 0.1401          | 0.7866    | 0.8629 | 0.8230 | 0.9660   |
+| 0.0796        | 6.67  | 1500 | 0.1402          | 0.7956    | 0.8755 | 0.8336 | 0.9677   |
+| 0.0561        | 8.89  | 2000 | 0.1419          | 0.8094    | 0.8793 | 0.8429 | 0.9700   |
+| 0.0416        | 11.11 | 2500 | 0.1562          | 0.8271    | 0.8793 | 0.8524 | 0.9687   |
+| 0.0306        | 13.33 | 3000 | 0.1761          | 0.8309    | 0.8890 | 0.8589 | 0.9702   |
+| 0.0233        | 15.56 | 3500 | 0.1785          | 0.8332    | 0.8798 | 0.8559 | 0.9701   |
+| 0.0188        | 17.78 | 4000 | 0.1875          | 0.8362    | 0.8847 | 0.8598 | 0.9694   |
+| 0.015         | 20.0  | 4500 | 0.1918          | 0.8359    | 0.8851 | 0.8598 | 0.9700   |
 
 
 ### Framework versions