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: 0.7634
-- Validation Loss: 0.9033
-- Train Mae: 0.4370
-- Epoch: 3
+- Train Loss: 0.5959
+- Validation Loss: 0.9241
+- Train Mae: 0.4173
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.9948     | 0.8706          | 0.4449    | 1     |
 | 0.9141     | 0.8791          | 0.4055    | 2     |
 | 0.7634     | 0.9033          | 0.4370    | 3     |
+| 0.5959     | 0.9241          | 0.4173    | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e47dad4a7d87a29a472bb393d575008ff3d52f8c9c6b7117017b85cabcc978d
+oid sha256:ed4393da2fb1bc3434cf09aad213f0cbb36f9046777ca5ff566a43f771180a86
 size 438232356