End of training
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 3.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| No log | 1.0 | 1 | 3.
|
52 |
-
| No log | 2.0 | 2 | 3.
|
53 |
-
| No log | 3.0 | 3 | 3.
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
- Transformers 4.42.4
|
59 |
-
- Pytorch 2.
|
60 |
- Datasets 2.21.0
|
61 |
- Tokenizers 0.19.1
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 3.7740
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| No log | 1.0 | 1 | 3.7728 |
|
52 |
+
| No log | 2.0 | 2 | 3.7735 |
|
53 |
+
| No log | 3.0 | 3 | 3.7740 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
- Transformers 4.42.4
|
59 |
+
- Pytorch 2.4.0+cu121
|
60 |
- Datasets 2.21.0
|
61 |
- Tokenizers 0.19.1
|
runs/Aug28_07-03-59_f0b6c09af1ef/events.out.tfevents.1724828640.f0b6c09af1ef.466.0
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 sha256:4305819b626f80d651591c220f00cbb47149e529d4d09492907faffd3ac3d8a0
|
3 |
+
size 6354
|
runs/Aug28_07-03-59_f0b6c09af1ef/events.out.tfevents.1724828728.f0b6c09af1ef.466.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:630fbdd1188821843c25c2f72acb58df1113cf150e645a207e4920694c7caba9
|
3 |
+
size 354
|