Training in progress epoch 3

README.md

@@ -15,14 +15,14 @@ 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: 3.4617
-- Validation Loss: 1.8004
-- Train Rouge1: 4.7218
-- Train Rouge2: 0.2888
-- Train Rougel: 4.7218
-- Train Rougelsum: 4.6723
-- Train Gen Len: 11.2723
-- Epoch: 2
+- Train Loss: 2.8272
+- Validation Loss: 1.7197
+- Train Rouge1: 6.1410
+- Train Rouge2: 0.8251
+- Train Rougel: 6.1410
+- Train Rougelsum: 6.0113
+- Train Gen Len: 11.1634
+- Epoch: 3
 
 ## Model description
 
@@ -51,6 +51,7 @@ The following hyperparameters were used during training:
 | 9.2952     | 2.6353          | 1.5618       | 0.0          | 1.5117       | 1.5288          | 16.5347       | 0     |
 | 4.7507     | 1.8159          | 5.5776       | 0.2888       | 5.5611       | 5.5281          | 12.2475       | 1     |
 | 3.4617     | 1.8004          | 4.7218       | 0.2888       | 4.7218       | 4.6723          | 11.2723       | 2     |
+| 2.8272     | 1.7197          | 6.1410       | 0.8251       | 6.1410       | 6.0113          | 11.1634       | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1719307739.c8f33d5a2397.1942.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5a38974b9815b8afc62a97e41fdb63264968ff0570fc53384fc698a81d7d19
-size 4548690
+oid sha256:10d2d2ddc5300f2fddb8b5541603687a8ff380d3b07265106bb5f38694ccf6d6
+size 4549112

logs/validation/events.out.tfevents.1719307957.c8f33d5a2397.1942.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9c4c465c2791c34e328666fd837fa1e455414d0b4d05770a96d1022f1e9d23
-size 544
+oid sha256:e969843babc9f0ec17c83ee62366eff604c442213b18b23c17ccd579e91a54f3
+size 700

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037d22294e8acd94ec0bfd6b7adcb215eb065ac792a7dbb8383923f3b2781931
+oid sha256:95b9566aeb6eb6840d12c18016d0604c48e409f690f2fd12ead85e067673a372
 size 2225556280