Training in progress epoch 21

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-large](https://huggingface.co/google/mt5-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.2367
-- Validation Loss: 1.0604
-- Train Rouge1: 8.0387
+- Train Loss: 1.0204
+- Validation Loss: 0.9582
+- Train Rouge1: 8.5809
 - Train Rouge2: 1.9307
-- Train Rougel: 7.9915
-- Train Rougelsum: 7.9679
-- Train Gen Len: 11.9356
-- Epoch: 18
+- Train Rougel: 8.4158
+- Train Rougelsum: 8.4512
+- Train Gen Len: 11.8317
+- Epoch: 21
 
 ## Model description
 
@@ -67,6 +67,9 @@ The following hyperparameters were used during training:
 | 1.3939     | 1.1446          | 8.1271       | 2.0627       | 8.0033       | 8.0858          | 11.7030       | 16    |
 | 1.3065     | 1.0837          | 7.7558       | 1.5677       | 7.5083       | 7.5908          | 11.8168       | 17    |
 | 1.2367     | 1.0604          | 8.0387       | 1.9307       | 7.9915       | 7.9679          | 11.9356       | 18    |
+| 1.1569     | 1.0071          | 7.6143       | 1.4356       | 7.4257       | 7.4965          | 11.8515       | 19    |
+| 1.0732     | 0.9713          | 8.5809       | 1.9307       | 8.4158       | 8.4512          | 11.8465       | 20    |
+| 1.0204     | 0.9582          | 8.5809       | 1.9307       | 8.4158       | 8.4512          | 11.8317       | 21    |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1710275260.c144174c8023.1261.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154fae3a6deff02fd3c3ac20e06ec271da5a099d16140679e8d564ce0f41e878
-size 13286426
+oid sha256:d3e8bc429b28712df046ab30dcdf785259db497b0f65d71d99fc651c218a5e83
+size 13287692

logs/validation/events.out.tfevents.1710275622.c144174c8023.1261.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4eff54699abd5da6f2a686707a6a148f9efee945be26db24eaca17e5d531cff
-size 3040
+oid sha256:8e65fba44704fbd924a676003a05597dacd84f2a841653794998b7de406de5fc
+size 3508

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77e7ecb696f2466dc7df137a53a55dcd46979e8e0514cdfaed6a6a0fd57e799
+oid sha256:68ca1747affc79976344bc7319f320f3625d5d8c517645ce589125be5fb80992
 size 6968370776