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: 4.7232
-- Validation Loss: 3.4923
-- Epoch: 3
+- Train Loss: 4.4641
+- Validation Loss: 3.4383
+- Epoch: 4
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 5.8732     | 3.7347          | 1     |
 | 5.1341     | 3.5766          | 2     |
 | 4.7232     | 3.4923          | 3     |
+| 4.4641     | 3.4383          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc51e4941c11d19bfff8e00c1abea257098f30d197dd3783d19017b513a3bde
+oid sha256:9f0a614d16dea36dd633171b631c8873ee491871c15be61a1c908b938b66f163
 size 2225556280