Training in progress epoch 2

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: 2.3539
-- Validation Loss: 2.2365
-- Train Accuracy: 0.6
-- Epoch: 1
+- Train Loss: 2.0114
+- Validation Loss: 1.9683
+- Train Accuracy: 0.7043
+- Epoch: 2
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:--------------:|:-----:|
 | 2.8547     | 2.5914          | 0.4261         | 0     |
 | 2.3539     | 2.2365          | 0.6            | 1     |
+| 2.0114     | 1.9683          | 0.7043         | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da08378f2ae4ca075ce71bb6f7670d0310a432cc18e17d9905428d3ff411bf0
+oid sha256:1f9adc6b63809d1e0d08140ab33d233aa684932870dc99d344a808d115f96077
 size 409420128