Training in progress epoch 4

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5791
-- Validation Loss: 0.2622
-- Train Accuracy: 0.9756
-- Epoch: 2
+- Train Loss: 0.2037
+- Validation Loss: 0.1631
+- Train Accuracy: 0.9747
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,8 @@ The following hyperparameters were used during training:
 | 3.5609     | 1.7191          | 0.8982         | 0     |
 | 1.3722     | 0.5564          | 0.9644         | 1     |
 | 0.5791     | 0.2622          | 0.9756         | 2     |
+| 0.3105     | 0.1978          | 0.9724         | 3     |
+| 0.2037     | 0.1631          | 0.9747         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87061529acef2829f25367fb6b163569293a4fe4b05c274ed0df9df3ce6c835
+oid sha256:12792c8597a99b974cc26a996db360c63c488eca601bfa76c256c61c1c4693ab
 size 499332928