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 [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.6852
-- Validation Loss: 1.4512
-- Epoch: 3
+- Train Loss: 1.6216
+- Validation Loss: 1.4148
+- Epoch: 4
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 1.9706     | 1.5594          | 1     |
 | 1.7805     | 1.4850          | 2     |
 | 1.6852     | 1.4512          | 3     |
+| 1.6216     | 1.4148          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed27523a9992e59de54813fa87eac1e8b1ab335af0721e172e08ee751cd8a704
+oid sha256:0081e549e1ad29edf9a5772f3399852d22d7ebaa383064f69bcf8da07527c456
 size 2225556280