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: 0.6232
-- Validation Loss: 1.2145
-- Train Mae: 0.5472
-- Epoch: 3
+- Train Loss: 0.4062
+- Validation Loss: 1.3899
+- Train Mae: 0.5591
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.9734     | 0.9739          | 0.5262    | 1     |
 | 0.8669     | 1.0520          | 0.5472    | 2     |
 | 0.6232     | 1.2145          | 0.5472    | 3     |
+| 0.4062     | 1.3899          | 0.5591    | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb3a5e0575644c3c1970d195689de3be503d1795b0e3d6cc6c19274ff92817e
+oid sha256:36b89f24c2c590916c61227c1c9f232781d95614ae4a419f7db344c29d92f1bd
 size 438232356