aditya9729
commited on
Commit
·
2287e79
1
Parent(s):
ab61fc8
update model card README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# starcoder_sc_final_small_context
|
14 |
|
15 |
-
This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -41,6 +43,13 @@ The following hyperparameters were used during training:
|
|
41 |
- lr_scheduler_type: cosine
|
42 |
- num_epochs: 1
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
### Framework versions
|
45 |
|
46 |
- Transformers 4.30.0.dev0
|
|
|
12 |
|
13 |
# starcoder_sc_final_small_context
|
14 |
|
15 |
+
This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.5978
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
43 |
- lr_scheduler_type: cosine
|
44 |
- num_epochs: 1
|
45 |
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 0.619 | 1.0 | 156 | 0.5978 |
|
51 |
+
|
52 |
+
|
53 |
### Framework versions
|
54 |
|
55 |
- Transformers 4.30.0.dev0
|