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 [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: 0.0326
-- Accuracy: 0.995
+- Loss: 0.0021
+- 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   | 13   | 0.9566          | 0.89     |
-| No log        | 2.0   | 26   | 0.5442          | 0.96     |
-| No log        | 3.0   | 39   | 0.2138          | 0.995    |
-| No log        | 4.0   | 52   | 0.0846          | 0.995    |
-| No log        | 5.0   | 65   | 0.0500          | 0.995    |
-| No log        | 6.0   | 78   | 0.0385          | 0.995    |
-| No log        | 7.0   | 91   | 0.0331          | 0.995    |
-| No log        | 8.0   | 104  | 0.0313          | 0.995    |
-| No log        | 9.0   | 117  | 0.0326          | 0.995    |
-| No log        | 10.0  | 130  | 0.0326          | 0.995    |
+| No log        | 1.0   | 38   | 0.2409          | 0.985    |
+| No log        | 2.0   | 76   | 0.0548          | 0.985    |
+| No log        | 3.0   | 114  | 0.0084          | 1.0      |
+| No log        | 4.0   | 152  | 0.0057          | 1.0      |
+| No log        | 5.0   | 190  | 0.0036          | 1.0      |
+| No log        | 6.0   | 228  | 0.0028          | 1.0      |
+| No log        | 7.0   | 266  | 0.0025          | 1.0      |
+| No log        | 8.0   | 304  | 0.0023          | 1.0      |
+| No log        | 9.0   | 342  | 0.0021          | 1.0      |
+| No log        | 10.0  | 380  | 0.0021          | 1.0      |
 
 
 ### Framework versions