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 [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5350
-- Accuracy: 0.8438
+- Loss: 0.1180
+- Accuracy: 0.9875
 
 ## Model description
 
@@ -43,17 +43,23 @@ 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: 5
+- num_epochs: 11
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 10   | 0.8345          | 0.625    |
-| No log        | 2.0   | 20   | 0.7268          | 0.625    |
-| No log        | 3.0   | 30   | 0.6339          | 0.7063   |
-| No log        | 4.0   | 40   | 0.5610          | 0.825    |
-| No log        | 5.0   | 50   | 0.5350          | 0.8438   |
+| No log        | 1.0   | 10   | 0.8421          | 0.625    |
+| No log        | 2.0   | 20   | 0.7016          | 0.75     |
+| No log        | 3.0   | 30   | 0.5544          | 0.85     |
+| No log        | 4.0   | 40   | 0.4178          | 0.8938   |
+| No log        | 5.0   | 50   | 0.3177          | 0.9187   |
+| No log        | 6.0   | 60   | 0.2455          | 0.9187   |
+| No log        | 7.0   | 70   | 0.2007          | 0.9313   |
+| No log        | 8.0   | 80   | 0.1603          | 0.9563   |
+| No log        | 9.0   | 90   | 0.1396          | 0.975    |
+| No log        | 10.0  | 100  | 0.1243          | 0.9875   |
+| No log        | 11.0  | 110  | 0.1180          | 0.9875   |
 
 
 ### Framework versions