End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1246
-- Accuracy: 0.3335
+- Loss: 1.0244
+- Accuracy: 0.6537
 
 ## Model description
 
@@ -43,22 +43,17 @@ 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: 10
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 1.1113        | 1.0   | 1250  | 1.1024          | 0.3331   |
-| 1.1032        | 2.0   | 2500  | 1.1246          | 0.3335   |
-| 1.0991        | 3.0   | 3750  | 1.1081          | 0.3335   |
-| 1.0987        | 4.0   | 5000  | 1.1382          | 0.3335   |
-| 1.1021        | 5.0   | 6250  | 1.1003          | 0.3335   |
-| 1.099         | 6.0   | 7500  | 1.1112          | 0.3331   |
-| 1.0991        | 7.0   | 8750  | 1.1052          | 0.3335   |
-| 1.0941        | 8.0   | 10000 | 1.1018          | 0.3335   |
-| 1.0977        | 9.0   | 11250 | 1.0996          | 0.3335   |
-| 1.0944        | 10.0  | 12500 | 1.1055          | 0.3335   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.1189        | 1.0   | 1251 | 1.1015          | 0.3335   |
+| 0.8798        | 2.0   | 2502 | 1.0573          | 0.5392   |
+| 0.6903        | 3.0   | 3753 | 0.9387          | 0.6348   |
+| 0.529         | 4.0   | 5004 | 0.9379          | 0.6513   |
+| 0.4211        | 5.0   | 6255 | 1.0244          | 0.6537   |
 
 
 ### Framework versions