Training in progress epoch 8

README.md

@@ -14,9 +14,9 @@ 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: 4.7338
-- Validation Loss: 4.4708
-- Epoch: 0
+- Train Loss: 4.3759
+- Validation Loss: 4.1950
+- Epoch: 8
 
 ## Model description
 
@@ -43,6 +43,14 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 4.7338     | 4.4708          | 0     |
+| 4.6456     | 4.4094          | 1     |
+| 4.5894     | 4.3608          | 2     |
+| 4.5385     | 4.3203          | 3     |
+| 4.5248     | 4.2885          | 4     |
+| 4.4042     | 4.2556          | 5     |
+| 4.4203     | 4.2326          | 6     |
+| 4.4128     | 4.2126          | 7     |
+| 4.3759     | 4.1950          | 8     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1676488037.a83b53361a22.1544.8.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec86fff5f620c5185f0af7018b72f182e0de2b7d7130c60375801e9354ca516
-size 3024818
+oid sha256:1a7b4b38b044cded83603fe077f38d4a15867a830e388a684941b8716c138cee
+size 3025362

logs/validation/events.out.tfevents.1676488041.a83b53361a22.1544.9.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e398f9b8e633f1ea758b6c2010a12e6b9c9386efffb0ad13905f39beb603ff3
-size 193
+oid sha256:67a693896ba1d42cb2b6bcb592b0c2554a63b0f8b1405bf561251a77b94beaab
+size 1433

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031a3396c407710e98c5d2656847639369a4a0b28bacb65f8bcd4163756ebfb1
+oid sha256:1157624e67fd841abe8ee88eb615fb1524eb6adbf9ddb4c0e0112ecf68a5c957
 size 373902848