End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2312
+- Loss: 0.2623
 
 ## Model description
 
@@ -46,16 +46,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2772        | 1.0   | 443  | 0.3078          |
-| 0.2298        | 2.0   | 886  | 0.3452          |
-| 0.2419        | 3.0   | 1329 | 0.2918          |
-| 0.1076        | 4.0   | 1772 | 0.3518          |
-| 0.1463        | 5.0   | 2215 | 0.2290          |
-| 0.0823        | 6.0   | 2658 | 0.2232          |
-| 0.117         | 7.0   | 3101 | 0.2131          |
-| 0.0313        | 8.0   | 3544 | 0.2125          |
-| 0.0577        | 9.0   | 3987 | 0.2179          |
-| 0.0777        | 10.0  | 4430 | 0.2312          |
+| 0.3388        | 1.0   | 443  | 0.4651          |
+| 0.3435        | 2.0   | 886  | 0.3720          |
+| 0.2449        | 3.0   | 1329 | 0.3122          |
+| 0.1175        | 4.0   | 1772 | 0.3218          |
+| 0.1389        | 5.0   | 2215 | 0.3442          |
+| 0.149         | 6.0   | 2658 | 0.2398          |
+| 0.1102        | 7.0   | 3101 | 0.2547          |
+| 0.0479        | 8.0   | 3544 | 0.2352          |
+| 0.0651        | 9.0   | 3987 | 0.2485          |
+| 0.0806        | 10.0  | 4430 | 0.2623          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edae7deb7249e8065f9da318b04c4e5d53dfb7c560b92f8c9acfcc7cdedb8725
+oid sha256:bb5534fe2da667670d4573836309d688d6c60ac1cfe278ad584d439866e4efc5
 size 711443456