Training in progress epoch 6

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: 0.6760
-- Train Accuracy: 0.5998
-- Validation Loss: 0.7845
-- Validation Accuracy: 0.5696
-- Epoch: 5
+- Train Loss: 0.6418
+- Train Accuracy: 0.6024
+- Validation Loss: 0.7774
+- Validation Accuracy: 0.5724
+- Epoch: 6
 
 ## Model description
 
@@ -51,6 +51,7 @@ The following hyperparameters were used during training:
 | 0.7395     | 0.5818         | 0.7777          | 0.5682              | 3     |
 | 0.7011     | 0.5931         | 0.7836          | 0.5708              | 4     |
 | 0.6760     | 0.5998         | 0.7845          | 0.5696              | 5     |
+| 0.6418     | 0.6024         | 0.7774          | 0.5724              | 6     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5c91b685fa3d4732a1abbadb3f93909dc6dcbcbc2e25843b5a53798c26e9a6
+oid sha256:5d176bf75828a66ed3fa1def89ae9f9aa0e45c6b8a1948697fa65d71a287537d
 size 1113185960