Training in progress epoch 0

README.md

@@ -15,12 +15,12 @@ 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: 0.4378
-- Train Binary Accuracy: 0.8192
-- Validation Loss: 0.4556
-- Validation Binary Accuracy: 0.8096
-- Train Accuracy: 0.3119
-- Epoch: 2
+- Train Loss: 0.3433
+- Train Binary Accuracy: 0.8777
+- Validation Loss: 0.5065
+- Validation Binary Accuracy: 0.8114
+- Train Accuracy: 0.4392
+- Epoch: 0
 
 ## Model description
 
@@ -46,9 +46,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Binary Accuracy | Validation Loss | Validation Binary Accuracy | Train Accuracy | Epoch |
 |:----------:|:---------------------:|:---------------:|:--------------------------:|:--------------:|:-----:|
-| 0.4827     | 0.8150                | 0.4821          | 0.7901                     | 0.8005         | 0     |
-| 0.4956     | 0.7784                | 0.7012          | 0.5092                     | 0.4392         | 1     |
-| 0.4378     | 0.8192                | 0.4556          | 0.8096                     | 0.3119         | 2     |
+| 0.3433     | 0.8777                | 0.5065          | 0.8114                     | 0.4392         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfd66a075c335c1a6be9eb6a6ea342f70efd2d5a84ad006c0fd164c6b822349
+oid sha256:cbb1e97eed5fa5531a4d195c934d4c1095aca713fd142123c4b2bf7dd2a437fe
 size 498878272