Training in progress epoch 3

README.md

@@ -14,10 +14,10 @@ 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:
-- Train Loss: 0.1183
-- Validation Loss: 0.1870
-- Train Accuracy: 0.9438
-- Epoch: 2
+- Train Loss: 0.0825
+- Validation Loss: 0.1853
+- Train Accuracy: 0.9392
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.3284     | 0.2441          | 0.9164         | 0     |
 | 0.1970     | 0.1913          | 0.9316         | 1     |
 | 0.1183     | 0.1870          | 0.9438         | 2     |
+| 0.0825     | 0.1853          | 0.9392         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7702ef900e46e846ad21704ca7672e7eeea98fc6558e81f5059c6a1f42d1b9dc
+oid sha256:b1da9b5336b650f8410c0ea6732cfa8c214dade9874a1b1aff8c4d6aeacc9bbb
 size 711707928