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: 2.2462
-- Validation Loss: 2.0331
-- Train Accuracy: 0.6579
-- Epoch: 2
+- Train Loss: 1.9850
+- Validation Loss: 1.7608
+- Train Accuracy: 0.7632
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 2.8885     | 2.6740          | 0.1316         | 0     |
 | 2.5028     | 2.3158          | 0.4737         | 1     |
 | 2.2462     | 2.0331          | 0.6579         | 2     |
+| 1.9850     | 1.7608          | 0.7632         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a6b3df72f2d68a3d8b11424dde4344915a3179c5aa5288210e15640214cf28
+oid sha256:ac08786481b559e32b1aeb53e089b0199f3e005750553ce29d737bf656f95ffb
 size 409423204