Training in progress epoch 4

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-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5222
-- Validation Loss: 0.4738
+- Train Loss: 0.4622
+- Validation Loss: 0.4601
 - Train Accuracy: 0.9375
-- Epoch: 3
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.5836     | 0.5508          | 0.8125         | 1     |
 | 0.6074     | 0.5035          | 0.9375         | 2     |
 | 0.5222     | 0.4738          | 0.9375         | 3     |
+| 0.4622     | 0.4601          | 0.9375         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ced187708785d2bb53f93f77e9c9913eb14192f6c62f4113204ac9c96aa399
+oid sha256:651ae3f7e89531b0d5c8ae2d137180177b383f500ebcd244542248cb1864acbb
 size 409364760