Training in progress epoch 3
Browse files- README.md +4 -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 [humarin/chatgpt_paraphraser_on_T5_base](https://huggingface.co/humarin/chatgpt_paraphraser_on_T5_base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 2.
|
19 |
-
- Validation Loss: 2.
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
|
|
46 |
| 2.9673 | 2.3630 | 0 |
|
47 |
| 2.5094 | 2.2455 | 1 |
|
48 |
| 2.3836 | 2.1726 | 2 |
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [humarin/chatgpt_paraphraser_on_T5_base](https://huggingface.co/humarin/chatgpt_paraphraser_on_T5_base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 2.3024
|
19 |
+
- Validation Loss: 2.1257
|
20 |
+
- Epoch: 3
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
46 |
| 2.9673 | 2.3630 | 0 |
|
47 |
| 2.5094 | 2.2455 | 1 |
|
48 |
| 2.3836 | 2.1726 | 2 |
|
49 |
+
| 2.3024 | 2.1257 | 3 |
|
50 |
|
51 |
|
52 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089544048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd73d58ec5e7719b60583e65e2aff74233189e7f8bca767805f57a2a107f054
|
3 |
size 1089544048
|