Training in progress epoch 4

README.md

@@ -14,11 +14,11 @@ 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: 5.3602
-- Train Accuracy: 0.0433
-- Validation Loss: 5.2734
-- Validation Accuracy: 0.0432
-- Epoch: 3
+- Train Loss: 5.2285
+- Train Accuracy: 0.0444
+- Validation Loss: 5.1562
+- Validation Accuracy: 0.0442
+- Epoch: 4
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 6.3670     | 0.0318         | 5.7812          | 0.0342              | 1     |
 | 5.6051     | 0.0380         | 5.4414          | 0.0420              | 2     |
 | 5.3602     | 0.0433         | 5.2734          | 0.0432              | 3     |
+| 5.2285     | 0.0444         | 5.1562          | 0.0442              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b393e8737400889570c4ab1b012ae7583adddff01becc1cbeee0d1bb6184f4e8
+oid sha256:a1d7114252fb5d480a7821c1a5bbd03a4f530fe1b935007c8f17107a0ea0a672
 size 499741936