Training in progress epoch 4

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [csebuetnlp/banglat5](https://huggingface.co/csebuetnlp/banglat5) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4892
-- Validation Loss: 0.2174
-- Epoch: 3
+- Train Loss: 0.3866
+- Validation Loss: 0.1928
+- Epoch: 4
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 1.3374     | 0.5028          | 1     |
 | 0.7359     | 0.2955          | 2     |
 | 0.4892     | 0.2174          | 3     |
+| 0.3866     | 0.1928          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e54836de8572237253126fd7d0798f77d86505640dfe07a0f636b73e0bd1a8
+oid sha256:6d614b20d254f3d95e8be6e073475526d757cf5be128121e2da3de9a50ff2ba7
 size 1188285040