Model save

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8615819209039548
+      value: 0.8475513428120063
     - name: Recall
       type: recall
-      value: 0.8818669971086328
+      value: 0.8864105741429161
     - name: F1
       type: f1
-      value: 0.8716064502959787
+      value: 0.8665455279628508
     - name: Accuracy
       type: accuracy
-      value: 0.9709691438504998
+      value: 0.9683326090105752
 ---
 
 <!-- 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: 0.1178
-- Precision: 0.8616
-- Recall: 0.8819
-- F1: 0.8716
-- Accuracy: 0.9710
+- Loss: 0.1632
+- Precision: 0.8476
+- Recall: 0.8864
+- F1: 0.8665
+- Accuracy: 0.9683
 
 ## Model description
 
@@ -68,22 +68,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 225  | 0.1357          | 0.7953    | 0.8315 | 0.8130 | 0.9620   |
-| No log        | 2.0   | 450  | 0.1056          | 0.8245    | 0.8691 | 0.8462 | 0.9687   |
-| 0.21          | 3.0   | 675  | 0.1064          | 0.8487    | 0.8831 | 0.8656 | 0.9698   |
-| 0.21          | 4.0   | 900  | 0.1198          | 0.8442    | 0.8839 | 0.8636 | 0.9704   |
-| 0.0589        | 5.0   | 1125 | 0.1178          | 0.8616    | 0.8819 | 0.8716 | 0.9710   |
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.208         | 1.0   | 7193  | 0.1642          | 0.8031    | 0.8509 | 0.8263 | 0.9620   |
+| 0.149         | 2.0   | 14386 | 0.1812          | 0.8426    | 0.8781 | 0.8600 | 0.9664   |
+| 0.0798        | 3.0   | 21579 | 0.1632          | 0.8476    | 0.8864 | 0.8665 | 0.9683   |
 
 
 ### Framework versions