End of training

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: 10.0060
-- Validation Loss: 4.3897
-- Epoch: 0
+- Train Loss: 4.0749
+- Validation Loss: 3.3854
+- Epoch: 7
 
 ## Model description
 
@@ -43,6 +43,13 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 10.0060    | 4.3897          | 0     |
+| 5.9039     | 3.8382          | 1     |
+| 5.1623     | 3.6476          | 2     |
+| 4.7477     | 3.5488          | 3     |
+| 4.4688     | 3.4721          | 4     |
+| 4.2706     | 3.4173          | 5     |
+| 4.1381     | 3.3921          | 6     |
+| 4.0749     | 3.3854          | 7     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047e4dffe9a2975120e4b4fbd9b181e0370cd22aeaa451de22c73b6164ffc13b
+oid sha256:ec82644b7ca3f1a097765c40f938d19ff5f5a16f9e8b8d15cf647bef09c2eef9
 size 1201092992