Training complete
Browse files- README.md +7 -5
- pytorch_model.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [Tiabet/kogpt2-base-v2-finetuned-koGPT-complete_story](https://huggingface.co/Tiabet/kogpt2-base-v2-finetuned-koGPT-complete_story) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 3.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -41,13 +41,15 @@ The following hyperparameters were used during training:
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
-
| Training Loss | Epoch | Step
|
49 |
-
|
50 |
-
| 3.
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [Tiabet/kogpt2-base-v2-finetuned-koGPT-complete_story](https://huggingface.co/Tiabet/kogpt2-base-v2-finetuned-koGPT-complete_story) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.2092
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 3.2518 | 1.0 | 3755 | 2.9790 |
|
51 |
+
| 3.8162 | 2.0 | 7510 | 2.9607 |
|
52 |
+
| 3.2811 | 3.0 | 11265 | 3.2092 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500713309
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51a55c456d1256fdb05afad7947223d06ff1afb64b8abb3c285f19c12a02ee06
|
3 |
size 500713309
|