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: 9.6302
-- Validation Loss: 4.2399
-- Epoch: 0
+- Train Loss: 3.9844
+- Validation Loss: 3.3610
+- Epoch: 7
 
 ## Model description
 
@@ -43,6 +43,13 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 9.6302     | 4.2399          | 0     |
+| 5.7657     | 3.7191          | 1     |
+| 4.9972     | 3.5931          | 2     |
+| 4.6081     | 3.5038          | 3     |
+| 4.3425     | 3.4322          | 4     |
+| 4.1758     | 3.3950          | 5     |
+| 4.0512     | 3.3649          | 6     |
+| 3.9844     | 3.3610          | 7     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c504bde652d2b729158b743202fb144aa93c4b0630fdb634b826dd5cf7366bd7
+oid sha256:f7e25401af166cbee8e8d6eb57229b569eccfc6889fc9469aa26bd06c7f9f89b
 size 1201092992