Model save
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- trl
|
6 |
- sft
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# temp-0.5-distilled-code-llama
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: constant
|
45 |
- lr_scheduler_warmup_ratio: 0.03
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Framework versions
|
49 |
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: anudaw/temp-0.5-distilled-code-llama
|
4 |
tags:
|
5 |
- trl
|
6 |
- sft
|
|
|
15 |
|
16 |
# temp-0.5-distilled-code-llama
|
17 |
|
18 |
+
This model is a fine-tuned version of [anudaw/temp-0.5-distilled-code-llama](https://huggingface.co/anudaw/temp-0.5-distilled-code-llama) on an unknown dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: constant
|
45 |
- lr_scheduler_warmup_ratio: 0.03
|
46 |
+
- num_epochs: 5
|
47 |
|
48 |
### Framework versions
|
49 |
|