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: 0.3585
-- Validation Loss: 0.3007
+- Train Loss: 0.2822
+- Validation Loss: 0.2787
 - Train Accuracy: 1.0
-- Epoch: 3
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.5522     | 0.4402          | 1.0            | 1     |
 | 0.4601     | 0.3570          | 1.0            | 2     |
 | 0.3585     | 0.3007          | 1.0            | 3     |
+| 0.2822     | 0.2787          | 1.0            | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad42756897e6ca0da52f390eb5e1442975706ad3044fee5a21886eb555b449a1
+oid sha256:a9cfef14d0c5227e6d95020221023174b6df01f445872b62a8f139899f7607be
 size 409364760