End of training

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+base_model: microsoft/deberta-v3-small
 tags:
 - generated_from_trainer
 metrics:
@@ -19,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0667
-- Precision: 0.6659
-- Recall: 0.7619
-- F1: 0.7106
-- Accuracy: 0.9781
+- Loss: 0.0636
+- Precision: 0.6312
+- Recall: 0.7311
+- F1: 0.6775
+- Accuracy: 0.9769
 
 ## Model description
 
@@ -48,20 +49,22 @@ 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: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 55   | 0.0751          | 0.6379    | 0.6218 | 0.6298 | 0.9723   |
-| No log        | 2.0   | 110  | 0.0675          | 0.6869    | 0.7465 | 0.7154 | 0.9772   |
-| No log        | 3.0   | 165  | 0.0667          | 0.6659    | 0.7619 | 0.7106 | 0.9781   |
+| No log        | 1.0   | 55   | 0.0843          | 0.4846    | 0.5294 | 0.5060 | 0.9683   |
+| No log        | 2.0   | 110  | 0.0697          | 0.5695    | 0.7115 | 0.6326 | 0.9729   |
+| No log        | 3.0   | 165  | 0.0652          | 0.6099    | 0.7423 | 0.6696 | 0.9754   |
+| No log        | 4.0   | 220  | 0.0636          | 0.6445    | 0.7185 | 0.6795 | 0.9772   |
+| No log        | 5.0   | 275  | 0.0636          | 0.6312    | 0.7311 | 0.6775 | 0.9769   |
 
 
 ### Framework versions
 
-- Transformers 4.30.2
+- Transformers 4.33.0
 - Pytorch 2.0.1+cu118
-- Datasets 2.12.0
+- Datasets 2.14.4
 - Tokenizers 0.13.3