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: 0.8657
-- Train Accuracy: 0.4491
-- Validation Loss: 0.8170
-- Validation Accuracy: 0.4334
-- Epoch: 2
+- Train Loss: 0.7807
+- Train Accuracy: 0.4664
+- Validation Loss: 0.7785
+- Validation Accuracy: 0.4459
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 1.7487     | 0.2210         | 1.1266          | 0.3799              | 0     |
 | 1.0173     | 0.4225         | 0.8678          | 0.4285              | 1     |
 | 0.8657     | 0.4491         | 0.8170          | 0.4334              | 2     |
+| 0.7807     | 0.4664         | 0.7785          | 0.4459              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1bdbb6a2af3cef84e59e250c0dc362b68c79b03a7337d9a7741098a300d039
+oid sha256:08b26c0b25d1f01b6bde22e6a1826c2301dd498a226115dfda580c36f612237f
 size 1113185960