Training in progress epoch 4

README.md

@@ -14,14 +14,14 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.2971
-- Validation Loss: 3.0305
-- Train Rouge1: 21.6173
-- Train Rouge2: 4.0001
-- Train Rougel: 16.2502
-- Train Rougelsum: 16.2302
-- Train Gen Len: 18.5
-- Epoch: 3
+- Train Loss: 3.2452
+- Validation Loss: 3.0086
+- Train Rouge1: 22.8085
+- Train Rouge2: 4.9522
+- Train Rougel: 17.8831
+- Train Rougelsum: 17.7797
+- Train Gen Len: 18.6
+- Epoch: 4
 
 ## Model description
 
@@ -51,6 +51,7 @@ The following hyperparameters were used during training:
 | 3.5034     | 3.1209          | 21.5417      | 3.8130       | 16.5211      | 16.5045         | 18.37         | 1     |
 | 3.3763     | 3.0605          | 21.0710      | 3.6133       | 15.7808      | 15.7437         | 18.33         | 2     |
 | 3.2971     | 3.0305          | 21.6173      | 4.0001       | 16.2502      | 16.2302         | 18.5          | 3     |
+| 3.2452     | 3.0086          | 22.8085      | 4.9522       | 17.8831      | 17.7797         | 18.6          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843cc25e12964058ddfb13a6d228ce65f57a3abc4c15a2459af8dd5610c1c02d
+oid sha256:8813af9a3d0383c3c8310489072e7657636a484d0592c76c1a0eeead2940c709
 size 373902848