Training in progress epoch 0

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: 0.0662
-- Validation Loss: 0.0924
-- Train Accuracy: 0.9724
-- Epoch: 1
+- Train Loss: 0.0169
+- Validation Loss: 0.0850
+- Train Accuracy: 0.9762
+- Epoch: 0
 
 ## Model description
 
@@ -43,8 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.1648     | 0.0986          | 0.9697         | 0     |
-| 0.0662     | 0.0924          | 0.9724         | 1     |
+| 0.0169     | 0.0850          | 0.9762         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eda00929612a00e03bc703d5a6bbfbc1be90bf857730f2e05b8305522e606988
+oid sha256:873851503171ca7f431887e840c7f0b7a77fbf86a906a13857f00d9434bdafe3
 size 409367836