Training in progress epoch 0
Browse files- README.md +4 -13
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -16,9 +16,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Train Loss: 1.
|
20 |
-
- Validation Loss: 1.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -44,16 +44,7 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Train Loss | Validation Loss | Epoch |
|
46 |
|:----------:|:---------------:|:-----:|
|
47 |
-
|
|
48 |
-
| 2.0425 | 1.9519 | 1 |
|
49 |
-
| 2.0092 | 1.9229 | 2 |
|
50 |
-
| 1.9794 | 1.9025 | 3 |
|
51 |
-
| 1.9528 | 1.8787 | 4 |
|
52 |
-
| 1.9269 | 1.8583 | 5 |
|
53 |
-
| 1.9049 | 1.8418 | 6 |
|
54 |
-
| 1.8832 | 1.8287 | 7 |
|
55 |
-
| 1.8640 | 1.8091 | 8 |
|
56 |
-
| 1.8440 | 1.7976 | 9 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Train Loss: 1.8274
|
20 |
+
- Validation Loss: 1.7835
|
21 |
+
- Epoch: 0
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
44 |
|
45 |
| Train Loss | Validation Loss | Epoch |
|
46 |
|:----------:|:---------------:|:-----:|
|
47 |
+
| 1.8274 | 1.7835 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 327745472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb15b83510bcaa57e272e7f1b7d1069ab390b67819bb5e62d5826737079fcbba
|
3 |
size 327745472
|