Model save

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [textattack/roberta-base-ag-news](https://huggingface.co/textattack/roberta-base-ag-news) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2200
-- Accuracy: 0.9443
-- F1: 0.9444
-- Precision: 0.9444
-- Recall: 0.9443
+- Loss: 0.2492
+- Accuracy: 0.9457
+- F1: 0.9456
+- Precision: 0.9456
+- Recall: 0.9457
 
 ## Model description
 
@@ -49,13 +49,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.108         | 1.0   | 3750 | 0.2200          | 0.9443   | 0.9444 | 0.9444    | 0.9443 |
+| 0.073         | 1.0   | 3750 | 0.2088          | 0.9417   | 0.9416 | 0.9419    | 0.9417 |
+| 0.0576        | 2.0   | 7500 | 0.2492          | 0.9457   | 0.9456 | 0.9456    | 0.9457 |
 
 
 ### Framework versions