Training in progress epoch 0

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: 2.7632
-- Validation Loss: 2.3667
-- Train Rouge1: 15.3586
-- Train Rouge2: 2.3426
-- Train Rougel: 12.8731
-- Train Rougelsum: 13.0251
-- Train Gen Len: 18.61
-- Epoch: 2
+- Train Loss: 3.8204
+- Validation Loss: 3.2757
+- Train Rouge1: 18.2829
+- Train Rouge2: 2.7616
+- Train Rougel: 14.7101
+- Train Rougelsum: 14.7047
+- Train Gen Len: 18.59
+- Epoch: 0
 
 ## Model description
 
@@ -47,9 +47,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
 |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
-| 3.8847     | 3.0992          | 15.4467      | 1.9295       | 12.5292      | 12.5098         | 18.99         | 0     |
-| 3.1345     | 2.6184          | 13.9583      | 1.5693       | 10.9544      | 11.1577         | 19.0          | 1     |
-| 2.7632     | 2.3667          | 15.3586      | 2.3426       | 12.8731      | 13.0251         | 18.61         | 2     |
+| 3.8204     | 3.2757          | 18.2829      | 2.7616       | 14.7101      | 14.7047         | 18.59         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2813bb20232077ad11ff12f9f78cbfcc60e218f6b0993f53e26fb906ea97c7c6
+oid sha256:c7865f0e10debac0eb25d4f50fec76498ba7e5df032ffbb47346f3ffcded182d
 size 242301848