Training in progress epoch 4

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.9903
-- Train Accuracy: 0.3952
-- Validation Loss: 1.1114
-- Validation Accuracy: 0.3790
-- Epoch: 3
+- Train Loss: 0.8813
+- Train Accuracy: 0.4204
+- Validation Loss: 1.1030
+- Validation Accuracy: 0.3787
+- Epoch: 4
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 1.4273     | 0.3085         | 1.2327          | 0.3523              | 1     |
 | 1.1660     | 0.3608         | 1.1347          | 0.3706              | 2     |
 | 0.9903     | 0.3952         | 1.1114          | 0.3790              | 3     |
+| 0.8813     | 0.4204         | 1.1030          | 0.3787              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b322e50bf20d9295883e292e0797e3efd7a10b505ebd0a13567054f838469634
+oid sha256:322c8b36685309e0ab23bd9fa129fa7208306be5b9e30c392e072effc734d328
 size 1113185960