Commit
•
dae4100
1
Parent(s):
8676baa
Training in progress epoch 58
Browse files- README.md +13 -3
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Train Loss: 0.
|
| 19 |
-
- Validation Loss: 0.
|
| 20 |
-
- Epoch:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -92,6 +92,16 @@ The following hyperparameters were used during training:
|
|
| 92 |
| 0.1367 | 0.1043 | 46 |
|
| 93 |
| 0.1278 | 0.1028 | 47 |
|
| 94 |
| 0.1308 | 0.1033 | 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
|
| 96 |
|
| 97 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 0.1159
|
| 19 |
+
- Validation Loss: 0.1001
|
| 20 |
+
- Epoch: 58
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 92 |
| 0.1367 | 0.1043 | 46 |
|
| 93 |
| 0.1278 | 0.1028 | 47 |
|
| 94 |
| 0.1308 | 0.1033 | 48 |
|
| 95 |
+
| 0.1266 | 0.1008 | 49 |
|
| 96 |
+
| 0.1127 | 0.1035 | 50 |
|
| 97 |
+
| 0.1263 | 0.0956 | 51 |
|
| 98 |
+
| 0.1281 | 0.0933 | 52 |
|
| 99 |
+
| 0.1209 | 0.0966 | 53 |
|
| 100 |
+
| 0.1139 | 0.0937 | 54 |
|
| 101 |
+
| 0.1174 | 0.0942 | 55 |
|
| 102 |
+
| 0.1137 | 0.0933 | 56 |
|
| 103 |
+
| 0.1183 | 0.0960 | 57 |
|
| 104 |
+
| 0.1159 | 0.1001 | 58 |
|
| 105 |
|
| 106 |
|
| 107 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 373902664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78ceb26b6c6cef0d0915b832ebfe4e44bb6af82d885da0fd50af3d8f2e45e8b2
|
| 3 |
size 373902664
|