End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0001
+- Loss: 0.0002
 - Accuracy: 1.0
 
 ## Model description
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 150  | 0.0018          | 1.0      |
-| No log        | 2.0   | 300  | 0.0007          | 1.0      |
-| No log        | 3.0   | 450  | 0.0004          | 1.0      |
-| 0.0295        | 4.0   | 600  | 0.0003          | 1.0      |
-| 0.0295        | 5.0   | 750  | 0.0002          | 1.0      |
-| 0.0295        | 6.0   | 900  | 0.0002          | 1.0      |
-| 0.0003        | 7.0   | 1050 | 0.0002          | 1.0      |
-| 0.0003        | 8.0   | 1200 | 0.0001          | 1.0      |
-| 0.0003        | 9.0   | 1350 | 0.0001          | 1.0      |
-| 0.0002        | 10.0  | 1500 | 0.0001          | 1.0      |
+| No log        | 1.0   | 150  | 0.0020          | 1.0      |
+| No log        | 2.0   | 300  | 0.0203          | 0.995    |
+| No log        | 3.0   | 450  | 0.0005          | 1.0      |
+| 0.0321        | 4.0   | 600  | 0.0003          | 1.0      |
+| 0.0321        | 5.0   | 750  | 0.0003          | 1.0      |
+| 0.0321        | 6.0   | 900  | 0.0002          | 1.0      |
+| 0.0004        | 7.0   | 1050 | 0.0002          | 1.0      |
+| 0.0004        | 8.0   | 1200 | 0.0002          | 1.0      |
+| 0.0004        | 9.0   | 1350 | 0.0002          | 1.0      |
+| 0.0002        | 10.0  | 1500 | 0.0002          | 1.0      |
 
 
 ### Framework versions