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: 0.6757
-- Validation Loss: 0.6684
+- Train Loss: 0.6773
+- Validation Loss: 0.6928
 - Train Accuracy: 0.6119
-- Epoch: 2
+- Epoch: 4
 
 ## Model description
 
@@ -46,6 +46,8 @@ The following hyperparameters were used during training:
 | 0.6936     | 0.6678          | 0.6119         | 0     |
 | 0.6691     | 0.6658          | 0.6119         | 1     |
 | 0.6757     | 0.6684          | 0.6119         | 2     |
+| 0.6825     | 0.6848          | 0.6119         | 3     |
+| 0.6773     | 0.6928          | 0.6119         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa44fdca3ff1664366a49e8fc35b95d9884b2750a5bf3051633862100f87f7ca
+oid sha256:5c4e2c02236f028f8ac4ebe395954618edcab7b819fb5ede1816021d2b736d8c
 size 438223192