Training in progress epoch 3

README.md

@@ -15,11 +15,11 @@ 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: 2.2064
-- Train Accuracy: 0.3648
-- Validation Loss: 1.9143
-- Validation Accuracy: 0.4416
-- Epoch: 2
+- Train Loss: 1.6431
+- Train Accuracy: 0.5494
+- Validation Loss: 1.5876
+- Validation Accuracy: 0.5411
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 2.8423     | 0.2313         | 2.5340          | 0.3593              | 0     |
 | 2.4502     | 0.3181         | 2.3051          | 0.3333              | 1     |
 | 2.2064     | 0.3648         | 1.9143          | 0.4416              | 2     |
+| 1.6431     | 0.5494         | 1.5876          | 0.5411              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c5c21fcff2d684a5fe45c43b9d26ed0eddeeab95e367159225f19e7b592d57
+oid sha256:c10c1572c317a04f3ff245a5438135f27601cd129e4e7e01d9d4cb36c7433a6d
 size 711818664