Training in progress epoch 3

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.6628
-- Validation Loss: 2.4317
-- Train Rougel: tf.Tensor(0.1261068, shape=(), dtype=float32)
-- Epoch: 2
+- Train Loss: 2.5738
+- Validation Loss: 2.3738
+- Train Rougel: tf.Tensor(0.13438718, shape=(), dtype=float32)
+- Epoch: 3
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 3.3729     | 2.7129          | tf.Tensor(0.108317316, shape=(), dtype=float32) | 0     |
 | 2.8239     | 2.5230          | tf.Tensor(0.11319066, shape=(), dtype=float32)  | 1     |
 | 2.6628     | 2.4317          | tf.Tensor(0.1261068, shape=(), dtype=float32)   | 2     |
+| 2.5738     | 2.3738          | tf.Tensor(0.13438718, shape=(), dtype=float32)  | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1697484835.820a0203d1d5.1674.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:204bc75f33e0060cf970f51900194713a46b7c796bad5c40988f89150d20ebfe
-size 2583315
+oid sha256:8de34f8fb39a815a04ec868acdd1ec92c3d71e2d3f752c50aa0e79b1007a7ef5
+size 2583453

logs/validation/events.out.tfevents.1697484967.820a0203d1d5.1674.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f3ac121df6677066985ebdb87c8bf21f0398be44e76c5416759bfc642a4c7b
-size 543
+oid sha256:ceaa2df548522eb5f9620feddbc076397acde59a3ee9508126f7dac98dc0f4f5
+size 699

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb0227b613fc486c25f8595b3a67c8190d3ba4ad3c6ed4c9882792496f3d4be
+oid sha256:c52a7957d21d71f370c6ce2aae8896180cffac20c113e319c1adfe5a6c969718
 size 373902664