Training in progress epoch 3

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: 7.9634
-- Validation Loss: 3.7626
-- Epoch: 0
+- Train Loss: 3.9338
+- Validation Loss: 3.2372
+- Epoch: 3
 
 ## Model description
 
@@ -43,6 +43,9 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 7.9634     | 3.7626          | 0     |
+| 4.9663     | 3.4392          | 1     |
+| 4.3167     | 3.2989          | 2     |
+| 3.9338     | 3.2372          | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64bb48d0de0a5079b8b126d1e057517cf129cfa14f3d9796f2c085692a5f358
+oid sha256:8c17463e5b20f229d362765652156e48409e015dedb5d0bd6477f8e32bd6adf8
 size 2225556280