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: 5.4626
-- Validation Loss: 3.6689
-- Epoch: 2
+- Train Loss: 4.9547
+- Validation Loss: 3.5794
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 10.5150    | 4.8716          | 0     |
 | 6.3881     | 3.9782          | 1     |
 | 5.4626     | 3.6689          | 2     |
+| 4.9547     | 3.5794          | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4e58b6817b49f4e64db995f213f0fbc84cce64dc2da1e73a99c73effdf8be7
+oid sha256:8a28db789bc473ea357ce1a14361b5a8d27ff95fe9d697979b628624e43ccaba
 size 2225556280