Training complete!

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2209
-- Accuracy: 0.9471
+- Loss: 0.3006
+- Accuracy: 0.9406
 
 ## Model description
 
@@ -44,22 +44,19 @@ 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: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 318  | 1.8516          | 0.7474   |
-| 2.1784        | 2.0   | 636  | 0.9798          | 0.8771   |
-| 2.1784        | 3.0   | 954  | 0.5581          | 0.9148   |
-| 0.8727        | 4.0   | 1272 | 0.3767          | 0.9326   |
-| 0.381         | 5.0   | 1590 | 0.2928          | 0.9426   |
-| 0.381         | 6.0   | 1908 | 0.2570          | 0.9435   |
-| 0.2238        | 7.0   | 2226 | 0.2370          | 0.9465   |
-| 0.1683        | 8.0   | 2544 | 0.2273          | 0.9465   |
-| 0.1683        | 9.0   | 2862 | 0.2221          | 0.9468   |
-| 0.1478        | 10.0  | 3180 | 0.2209          | 0.9471   |
+| No log        | 1.0   | 318  | 1.6434          | 0.7435   |
+| 1.9562        | 2.0   | 636  | 0.9006          | 0.8661   |
+| 1.9562        | 3.0   | 954  | 0.5509          | 0.9129   |
+| 0.8242        | 4.0   | 1272 | 0.4011          | 0.9313   |
+| 0.4197        | 5.0   | 1590 | 0.3346          | 0.9390   |
+| 0.4197        | 6.0   | 1908 | 0.3087          | 0.9384   |
+| 0.2973        | 7.0   | 2226 | 0.3006          | 0.9406   |
 
 
 ### Framework versions