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: 2.3113
-- Validation Loss: 2.0867
-- Train Accuracy: 0.4737
-- Epoch: 2
+- Train Loss: 2.2336
+- Validation Loss: 1.9643
+- Train Accuracy: 0.5
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 2.9423     | 2.5705          | 0.1842         | 0     |
 | 2.6021     | 2.2725          | 0.4474         | 1     |
 | 2.3113     | 2.0867          | 0.4737         | 2     |
+| 2.2336     | 1.9643          | 0.5            | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b11b19e4a88743e64e60b7cf15ff8047e2e1b9078fcb04af1d3d970e62fef8a
+oid sha256:90fd74e4ac0713c325be45bff3784e22a5caa8776427ca8fefd342b98f5649b6
 size 409423204