Training in progress epoch 3

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: 0.7972
-- Train Accuracy: 0.5688
-- Validation Loss: 0.7997
-- Validation Accuracy: 0.5624
-- Epoch: 2
+- Train Loss: 0.7395
+- Train Accuracy: 0.5818
+- Validation Loss: 0.7777
+- Validation Accuracy: 0.5682
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 1.1865     | 0.4781         | 0.9186          | 0.5364              | 0     |
 | 0.8841     | 0.5450         | 0.8210          | 0.5555              | 1     |
 | 0.7972     | 0.5688         | 0.7997          | 0.5624              | 2     |
+| 0.7395     | 0.5818         | 0.7777          | 0.5682              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc670252eb1aecc7228c7fc00434cb2f183dfddefbebfd01cfac71806f57298b
+oid sha256:f9c6e497e740169f6a014d39b5c47faf35751d78c64958c98ae8e12c7841fb73
 size 1113185960