Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
base_model: codellama/CodeLlama-7b-hf
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: codellama2-finetuned-codex-py
|
8 |
+
results: []
|
9 |
+
datasets:
|
10 |
+
- iamtarun/python_code_instructions_18k_alpaca
|
11 |
+
language:
|
12 |
+
- en
|
13 |
+
library_name: peft
|
14 |
+
pipeline_tag: text-generation
|
15 |
+
---
|
16 |
+
|
17 |
+
|
18 |
+
|
19 |
+
# codellama2-finetuned-codex-py
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
| Step | Training Loss |
|
34 |
+
|------|---------------|
|
35 |
+
| 10 | 0.792200 |
|
36 |
+
| 20 | 0.416100 |
|
37 |
+
| 30 | 0.348600 |
|
38 |
+
| 40 | 0.323200 |
|
39 |
+
| 50 | 0.316300 |
|
40 |
+
| 60 | 0.317500 |
|
41 |
+
| 70 | 0.333600 |
|
42 |
+
| 80 | 0.329500 |
|
43 |
+
| 90 | 0.333400 |
|
44 |
+
| 100 | 0.309900 |
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 0.0002
|
52 |
+
- train_batch_size: 8
|
53 |
+
- eval_batch_size: 8
|
54 |
+
- seed: 42
|
55 |
+
- gradient_accumulation_steps: 4
|
56 |
+
- total_train_batch_size: 32
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: cosine
|
59 |
+
- training_steps: 100
|
60 |
+
- mixed_precision_training: Native AMP
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.36.0.dev0
|
69 |
+
- Pytorch 2.0.0
|
70 |
+
- Datasets 2.1.0
|
71 |
+
- Tokenizers 0.15.0
|