update model card README.md
Browse files
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 [distilgpt2](https://huggingface.co/distilgpt2) on the recipe_nlg_lite dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -41,15 +41,17 @@ 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 | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 1.
|
51 |
-
| 1.
|
52 |
-
| 1.
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the recipe_nlg_lite dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.1328
|
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: 5.0
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 1.4765 | 1.0 | 765 | 1.2390 |
|
51 |
+
| 1.222 | 2.0 | 1530 | 1.1797 |
|
52 |
+
| 1.1884 | 3.0 | 2295 | 1.1524 |
|
53 |
+
| 1.1446 | 4.0 | 3060 | 1.1371 |
|
54 |
+
| 1.1458 | 5.0 | 3825 | 1.1328 |
|
55 |
|
56 |
|
57 |
### Framework versions
|