Training in progress epoch 3

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.1760
-- Validation Loss: 3.2321
-- Epoch: 2
+- Train Loss: 3.1495
+- Validation Loss: 3.1758
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 3.2691     | 3.2396          | 0     |
 | 3.2039     | 3.2204          | 1     |
 | 3.1760     | 3.2321          | 2     |
+| 3.1495     | 3.1758          | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77084c61b75a8e99f0e844e246492a7b129b2f7cbd6da7c3dd35d75ffaf8d2fa
+oid sha256:e1ca52bcef21b9344c579e8b66c41cee528ea953f12281a24f6dc17a19650e02
 size 2225556280