Training in progress epoch 4

README.md

@@ -15,14 +15,14 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.8071
-- Validation Loss: 2.9327
-- Train Rouge1: 0.1916
-- Train Rouge2: 0.0735
-- Train Rougel: 0.1506
-- Train Rougelsum: 0.1501
+- Train Loss: 3.5410
+- Validation Loss: 2.6951
+- Train Rouge1: 0.1943
+- Train Rouge2: 0.0749
+- Train Rougel: 0.1532
+- Train Rougelsum: 0.1527
 - Train Gen Len: 19.0
-- Epoch: 3
+- Epoch: 4
 
 ## Model description
 
@@ -52,6 +52,7 @@ The following hyperparameters were used during training:
 | 4.2189     | 3.4754          | 0.1988       | 0.0822       | 0.158        | 0.1579          | 19.0          | 1     |
 | 3.9742     | 3.1733          | 0.1988       | 0.0822       | 0.158        | 0.1579          | 19.0          | 2     |
 | 3.8071     | 2.9327          | 0.1916       | 0.0735       | 0.1506       | 0.1501          | 19.0          | 3     |
+| 3.5410     | 2.6951          | 0.1943       | 0.0749       | 0.1532       | 0.1527          | 19.0          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f24f5e9385ad1b54c04cf9f290ff78ea564d7007ebb5e404e1989ca4b2dead
+oid sha256:2b6ee2756d55642ca1b3328ac0ea2b3fa0d7919fd44ab8f4b3c8c679a03b8c04
 size 373902664