Training in progress epoch 13
Browse files
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 [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 2.
|
19 |
-
- Validation Loss: 4.
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -56,6 +56,7 @@ The following hyperparameters were used during training:
|
|
56 |
| 2.5699 | 3.9660 | 10 |
|
57 |
| 2.5262 | 3.9897 | 11 |
|
58 |
| 2.5002 | 4.0219 | 12 |
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 2.4636
|
19 |
+
- Validation Loss: 4.0540
|
20 |
+
- Epoch: 13
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
56 |
| 2.5699 | 3.9660 | 10 |
|
57 |
| 2.5262 | 3.9897 | 11 |
|
58 |
| 2.5002 | 4.0219 | 12 |
|
59 |
+
| 2.4636 | 4.0540 | 13 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
logs/train/events.out.tfevents.1711718173.e7f3963a7819.156.2.v2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b6aa754c74039256d288abcfa7b6a99658e5bd8b4879f9ddd3fbcf86c9858c6
|
3 |
+
size 966814
|
logs/validation/events.out.tfevents.1711718177.e7f3963a7819.156.3.v2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8129144b887da2c7145047ae942e0ce4876cb6d0fb9dec2b5c18804479c52e6
|
3 |
+
size 2260
|
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 sha256:1b6ac582d2273aba21191b72dcb8e0c3ef671f547b7150fb134e220e0f471963
|
3 |
size 327745472
|