Training in progress epoch 4

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7190
-- Train Accuracy: 0.0588
-- Validation Loss: 0.6563
-- Validation Accuracy: 0.0604
-- Epoch: 3
+- Train Loss: 0.6720
+- Train Accuracy: 0.0592
+- Validation Loss: 0.6636
+- Validation Accuracy: 0.0601
+- Epoch: 4
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 0.8735     | 0.0567         | 0.7660          | 0.0589              | 1     |
 | 0.7694     | 0.0574         | 0.7093          | 0.0584              | 2     |
 | 0.7190     | 0.0588         | 0.6563          | 0.0604              | 3     |
+| 0.6720     | 0.0592         | 0.6636          | 0.0601              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de945fb2131b4d2f5ec116748e5ed662ba48fc8c0620e26571dc69741cdb53a9
+oid sha256:a94e02e29f802b5d1d9c977a96f447a8d4b0fb32a958028f168fa14ef951290c
 size 475933304