Training in progress epoch 3

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5118
-- Validation Loss: 1.3326
-- Train Bleu: 27.2074
-- Train Gen Len: 42.2061
-- Epoch: 2
+- Train Loss: 0.4936
+- Validation Loss: 1.3441
+- Train Bleu: 27.4083
+- Train Gen Len: 42.1591
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 0.6844     | 1.3261          | 26.5988    | 42.1146       | 0     |
 | 0.5396     | 1.3241          | 26.8846    | 42.0145       | 1     |
 | 0.5118     | 1.3326          | 27.2074    | 42.2061       | 2     |
+| 0.4936     | 1.3441          | 27.4083    | 42.1591       | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1720194758.9cfa8e0229ed.526.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ed448f94570ad82a8ed777b65767a76a37e167b867ca4e7fa129ffe3eecd88
-size 5903733
+oid sha256:58e62e38eff7697650e82db5c426f5f2874aca01b5ee9e7132e694c2c61a9e28
+size 5903940

logs/validation/events.out.tfevents.1720196200.9cfa8e0229ed.526.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb85ba754d808a80402056b7e9d7470d62da9ab5503b2dcdec5ec9a844a0479
-size 544
+oid sha256:95de10df35ea92f3000f30386fb4fb93eb739a23125ef22e01bbc992d3ee39e0
+size 700

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45cd20f9ba2344f704fae5c467bc21ccff82691699ff9ac5bb6ac35bedc5f69d
+oid sha256:a699f72d2dd4ba3cfcaad4cf883c71dfee0e56a8a6d4f820765303c1aad998c4
 size 1089544048