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: 2.2749
-- Validation Loss: 2.2041
-- Train Accuracy: 0.4474
-- Epoch: 3
+- Train Loss: 2.1581
+- Validation Loss: 2.1831
+- Train Accuracy: 0.4737
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 2.5610     | 2.4772          | 0.3158         | 1     |
 | 2.4059     | 2.3114          | 0.4474         | 2     |
 | 2.2749     | 2.2041          | 0.4474         | 3     |
+| 2.1581     | 2.1831          | 0.4737         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a318e28a2be088b4eae3115bd7a12140a9b1e61abced72e66ce8b2de02468335
+oid sha256:61e865582d2c7edf881f7f49baf2e1baa00fdcb97f3cdbc4b29087565786c8e2
 size 409423204