Training in progress epoch 4

README.md

@@ -14,11 +14,11 @@ 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: 0.6974
-- Train Accuracy: 0.0590
-- Validation Loss: 0.6988
-- Validation Accuracy: 0.0589
-- Epoch: 3
+- Train Loss: 0.6641
+- Train Accuracy: 0.0599
+- Validation Loss: 0.5843
+- Validation Accuracy: 0.0609
+- Epoch: 4
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 0.8356     | 0.0571         | 0.7513          | 0.0585              | 1     |
 | 0.7771     | 0.0584         | 0.7556          | 0.0602              | 2     |
 | 0.6974     | 0.0590         | 0.6988          | 0.0589              | 3     |
+| 0.6641     | 0.0599         | 0.5843          | 0.0609              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ebf2b814a86055ee519d25b21a1018fe2a8372c772b9464a82d3bb882c0e1a4
+oid sha256:357729aeb5443c55d76996c942cfd54cda6ce7108ee14626387208bc57244aaf
 size 475933304