Training in progress epoch 26

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-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4321
-- Validation Loss: 0.7647
-- Train Rouge1: 7.9208
+- Train Loss: 0.4157
+- Validation Loss: 0.7598
+- Train Rouge1: 8.4866
 - Train Rouge2: 0.7921
-- Train Rougel: 7.9444
-- Train Rougelsum: 8.0387
-- Train Gen Len: 11.8069
-- Epoch: 25
+- Train Rougel: 8.4335
+- Train Rougelsum: 8.5573
+- Train Gen Len: 11.8218
+- Epoch: 26
 
 ## Model description
 
@@ -74,6 +74,7 @@ The following hyperparameters were used during training:
 | 0.4725     | 0.7612          | 7.9208       | 0.7921       | 7.9444       | 8.0387          | 11.8515       | 23    |
 | 0.4520     | 0.7772          | 7.9208       | 0.7921       | 7.9444       | 8.0387          | 11.8218       | 24    |
 | 0.4321     | 0.7647          | 7.9208       | 0.7921       | 7.9444       | 8.0387          | 11.8069       | 25    |
+| 0.4157     | 0.7598          | 8.4866       | 0.7921       | 8.4335       | 8.5573          | 11.8218       | 26    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1719308085.a9b0e98d27d1.484.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:348b0dfa7ff9c3aa2d1865dc40cef28d776994f67777ed610a0b9cd5e6208464
-size 6735001
+oid sha256:a60522247a07390ce1115c96156ae11f86fc746fac4880d7db8d6ca5458cdc7c
+size 6735423

logs/validation/events.out.tfevents.1719308413.a9b0e98d27d1.484.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4015e33a48633276baaf8a88b75f26dc095fb40feee93cb0a22d5a12e4e4ddc3
-size 4146
+oid sha256:1adfc14507c8d54c5dc16ce69ecb33fab7390bb8f48fa9c7dfe74bc512dab7fd
+size 4303

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ff34cb612175c175b5ce360639297c41e372eb9429dedf93311166cca70003
+oid sha256:56c27a330c10e7836cf26dd7763731f116e2891265f1c3d4685dd690b1e704d5
 size 3866872432