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: 2.0491
-- Validation Loss: 2.0340
-- Train Accuracy: 0.5122
-- Epoch: 3
+- Train Loss: 1.7890
+- Validation Loss: 1.7980
+- Train Accuracy: 0.6463
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 2.8571     | 2.6364          | 0.3902         | 1     |
 | 2.4461     | 2.2839          | 0.4634         | 2     |
 | 2.0491     | 2.0340          | 0.5122         | 3     |
+| 1.7890     | 1.7980          | 0.6463         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b639ac1b6f454a8d5f9959c28f2e2382e596822aa5c970fbc443b05b2727b0
+oid sha256:fe73ad6edde60a44921ca17eabef8027757a1129d2e68e95ecd0c10dcfa8ea46
 size 409469344