Training in progress epoch 3

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: 2.4059
-- Validation Loss: 2.3114
+- Train Loss: 2.2749
+- Validation Loss: 2.2041
 - Train Accuracy: 0.4474
-- Epoch: 2
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 2.8776     | 2.6967          | 0.0526         | 0     |
 | 2.5610     | 2.4772          | 0.3158         | 1     |
 | 2.4059     | 2.3114          | 0.4474         | 2     |
+| 2.2749     | 2.2041          | 0.4474         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd4258f38bc8fd6fa997cca83fc72f91ee980e751e97c71d6c306944f2a1cdd
+oid sha256:a318e28a2be088b4eae3115bd7a12140a9b1e61abced72e66ce8b2de02468335
 size 409423204