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: 0.6939
-- Validation Loss: 1.1868
-- Train Mae: 0.5210
-- Epoch: 3
+- Train Loss: 0.5225
+- Validation Loss: 1.2265
+- Train Mae: 0.5157
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.9342     | 1.0136          | 0.4094    | 1     |
 | 0.8664     | 1.0464          | 0.4370    | 2     |
 | 0.6939     | 1.1868          | 0.5210    | 3     |
+| 0.5225     | 1.2265          | 0.5157    | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6e072add6f4348f753b6b8c944ed74e073703ed321df44847bda1fd87774a2
+oid sha256:d75746e00db3567c8920752ec22cd541f1e819915d1e6259d5120f164ed264b8
 size 438232356