Training in progress epoch 3

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: 0.9141
-- Validation Loss: 0.8791
-- Train Mae: 0.4055
-- Epoch: 2
+- Train Loss: 0.7634
+- Validation Loss: 0.9033
+- Train Mae: 0.4370
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 1.0796     | 0.8943          | 0.4659    | 0     |
 | 0.9948     | 0.8706          | 0.4449    | 1     |
 | 0.9141     | 0.8791          | 0.4055    | 2     |
+| 0.7634     | 0.9033          | 0.4370    | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d020507b87643a75de1d551f9a7ec9b5492de9e134d132e0086ade873537b22
+oid sha256:8e47dad4a7d87a29a472bb393d575008ff3d52f8c9c6b7117017b85cabcc978d
 size 438232356