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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1552
-- Accuracy: 0.9548
+- Loss: 0.1529
+- Accuracy: 0.9555
 
 ## Model description
 
@@ -49,14 +49,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 494  | 0.9033          | 0.7660   |
-| 1.666         | 2.0   | 988  | 0.5476          | 0.8544   |
-| 0.7826        | 3.0   | 1482 | 0.3627          | 0.9018   |
-| 0.529         | 4.0   | 1976 | 0.2893          | 0.9206   |
-| 0.4172        | 5.0   | 2470 | 0.2254          | 0.9379   |
-| 0.3246        | 6.0   | 2964 | 0.1883          | 0.9452   |
-| 0.2703        | 7.0   | 3458 | 0.1646          | 0.9529   |
-| 0.233         | 8.0   | 3952 | 0.1552          | 0.9548   |
+| No log        | 1.0   | 491  | 0.8079          | 0.7950   |
+| 1.5652        | 2.0   | 982  | 0.5059          | 0.8689   |
+| 0.7283        | 3.0   | 1473 | 0.3466          | 0.9072   |
+| 0.504         | 4.0   | 1964 | 0.2646          | 0.9260   |
+| 0.3862        | 5.0   | 2455 | 0.2144          | 0.9414   |
+| 0.3071        | 6.0   | 2946 | 0.1885          | 0.9459   |
+| 0.2554        | 7.0   | 3437 | 0.1600          | 0.9540   |
+| 0.2235        | 8.0   | 3928 | 0.1529          | 0.9555   |
 
 
 ### Framework versions