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: 1.7380
-- Validation Loss: 1.7066
-- Train Accuracy: 0.6352
-- Epoch: 3
+- Train Loss: 1.4422
+- Validation Loss: 1.5095
+- Train Accuracy: 0.6855
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 2.7007     | 2.5022          | 0.4654         | 1     |
 | 2.1853     | 2.0269          | 0.5597         | 2     |
 | 1.7380     | 1.7066          | 0.6352         | 3     |
+| 1.4422     | 1.5095          | 0.6855         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d277cc1962452c61e3b5ed8dbab10aab60b6d5765e84b3805d1ef7ea813b207
+oid sha256:f85d72ffbd75965bb018c0dbfd98862aebf193281906045616029769128d870d
 size 409469344