Commit
•
7cc090b
1
Parent(s):
d68d31e
End of training
Browse files- README.md +5 -5
- generation_config.json +1 -1
- pytorch_model.bin +1 -1
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 [gpt2](https://huggingface.co/gpt2) on the ag_news 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 |
-
| 3.
|
52 |
-
| 2.
|
53 |
-
| 1.
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
-
- Transformers 4.34.
|
59 |
- Pytorch 2.0.1+cu118
|
60 |
- Datasets 2.14.4
|
61 |
- Tokenizers 0.14.0
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the ag_news dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 3.5432
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 3.52 | 0.53 | 200 | 3.6018 |
|
52 |
+
| 2.8991 | 1.07 | 400 | 3.5992 |
|
53 |
+
| 1.8674 | 1.6 | 600 | 3.5432 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
+
- Transformers 4.34.1
|
59 |
- Pytorch 2.0.1+cu118
|
60 |
- Datasets 2.14.4
|
61 |
- Tokenizers 0.14.0
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.34.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.34.1"
|
6 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497807197
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4b2baefa577d53e0c231d4756deae06559d3df76eaadab00aac51d98b538765
|
3 |
size 497807197
|