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-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0958
-- Validation Loss: 0.1931
-- Train Accuracy: 0.9348
-- Epoch: 2
+- Train Loss: 0.0433
+- Validation Loss: 0.2119
+- Train Accuracy: 0.9320
+- Epoch: 4
 
 ## Model description
 
@@ -46,6 +46,8 @@ The following hyperparameters were used during training:
 | 0.3301     | 0.2277          | 0.9150         | 0     |
 | 0.1607     | 0.1973          | 0.9235         | 1     |
 | 0.0958     | 0.1931          | 0.9348         | 2     |
+| 0.0592     | 0.2309          | 0.9292         | 3     |
+| 0.0433     | 0.2119          | 0.9320         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081fbefb05267397c23260db1cb21812cf332d150224661bf7e8d50e83e1b021
+oid sha256:f3c6ecbfe1818eb58990beec2afd2eb2372684ae1fe70cfdf8930a413ba76dff
 size 438223192