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-efficient-tiny](https://huggingface.co/google/t5-efficient-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.6068
-- Validation Loss: 3.5431
-- Train Rouge1: 20.4053
-- Train Rouge2: 3.9626
-- Train Rougel: 16.3460
-- Train Rougelsum: 16.3444
-- Train Gen Len: 15.884
-- Epoch: 3
+- Train Loss: 4.4877
+- Validation Loss: 3.4974
+- Train Rouge1: 21.2490
+- Train Rouge2: 4.2075
+- Train Rougel: 16.9993
+- Train Rougelsum: 16.9842
+- Train Gen Len: 16.678
+- Epoch: 4
 
 ## Model description
 
@@ -52,6 +52,7 @@ The following hyperparameters were used during training:
 | 5.1618     | 3.7340          | 19.5200      | 3.7088       | 16.1766      | 16.1763         | 15.528        | 1     |
 | 4.8511     | 3.6247          | 20.1377      | 3.7645       | 16.1460      | 16.1223         | 15.966        | 2     |
 | 4.6068     | 3.5431          | 20.4053      | 3.9626       | 16.3460      | 16.3444         | 15.884        | 3     |
+| 4.4877     | 3.4974          | 21.2490      | 4.2075       | 16.9993      | 16.9842         | 16.678        | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c211b2f99bc74eb0be7704a251bf26cf730c0b9139e6205bb0913b0c884d207b
+oid sha256:eddc80fd881772dfd0b02eb0968a66970485e119fd23a78e67cb42d2df5a9b6f
 size 128277296