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: 0.6991
-- Validation Loss: 0.8124
-- Train Mae: 0.4816
-- Epoch: 2
+- Train Loss: 0.4886
+- Validation Loss: 1.0170
+- Train Mae: 0.4934
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.8577     | 0.7504          | 0.4173    | 0     |
 | 0.7823     | 0.7742          | 0.4685    | 1     |
 | 0.6991     | 0.8124          | 0.4816    | 2     |
+| 0.4886     | 1.0170          | 0.4934    | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ac06e543fc8c17e078f8838399d1172a054e7351d080699ae4b2bd855426fa
+oid sha256:7633fc47543bbc798d7ea98a0e17eb8c0f8adb377127a9e19a30a21da2d01d8b
 size 438232356