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: 0.8855
-- Validation Loss: 1.1600
-- Train Mae: 0.7428
-- Epoch: 3
+- Train Loss: 0.6661
+- Validation Loss: 1.2828
+- Train Mae: 0.7021
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 1.0882     | 1.0187          | 0.6286    | 1     |
 | 1.0446     | 1.0533          | 0.6063    | 2     |
 | 0.8855     | 1.1600          | 0.7428    | 3     |
+| 0.6661     | 1.2828          | 0.7021    | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5457a5a0b8bfb9138b80286253977520fb0e81fd5afa416a137954dc252bc20d
+oid sha256:defb4bf2a52290cc91670198c4603a8c4a4f17dba7299b9cd27c4ea9b0b65134
 size 438232356