Training in progress epoch 3

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7354
-- Validation Loss: 0.8494
-- Train Accuracy: 0.6046
-- Epoch: 2
+- Train Loss: 0.6645
+- Validation Loss: 0.9047
+- Train Accuracy: 0.6080
+- Epoch: 3
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 1.0725     | 0.8868          | 0.6163         | 0     |
 | 0.8197     | 0.8660          | 0.6323         | 1     |
 | 0.7354     | 0.8494          | 0.6046         | 2     |
+| 0.6645     | 0.9047          | 0.6080         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b1ef75878a51082ed7b9c8130ae3e88a6786708592bc285053e53baeb5edd9
+oid sha256:13b5b29c750d010efd4de197b3415a0e95fbe8f7d9d673414f9ecbb1e6cfd86c
 size 433544484