|
--- |
|
datasets: |
|
- nampdn-ai/tiny-codes |
|
library_name: peft |
|
tags: |
|
- llama2 |
|
- llama2-7b |
|
- code generation |
|
- code-generation |
|
- code |
|
- instruct |
|
- instruct-code |
|
- code-alpaca |
|
- alpaca-instruct |
|
- alpaca |
|
- llama7b |
|
- gpt2 |
|
license: apache-2.0 |
|
--- |
|
## Training procedure |
|
We finetuned [Llama 2 7B model](https://huggingface.co/meta-llama/Llama-2-7b-hf) from Meta on [nampdn-ai/tiny-codes](https://huggingface.co/datasets/nampdn-ai/tiny-codes) for ~ 10,000 steps using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm). |
|
|
|
This dataset contains **1.63 million rows** and is a collection of short and clear code snippets that can help LLM models learn how to reason with both natural and programming languages. The dataset covers a wide range of programming languages, such as Python, TypeScript, JavaScript, Ruby, Julia, Rust, C++, Bash, Java, C#, and Go. It also includes two database languages: Cypher (for graph databases) and SQL (for relational databases) in order to study the relationship of entities. |
|
|
|
The finetuning session got completed in 53 hours and costed us ~ `$125` for the entire finetuning run! |
|
|
|
#### Hyperparameters & Run details: |
|
- Model Path: meta-llama/Llama-2-7b-hf |
|
- Dataset: nampdn-ai/tiny-codes |
|
- Learning rate: 0.0002 |
|
- Number of epochs: 1 (10k steps) |
|
- Data split: Training: 90% / Validation: 10% |
|
- Gradient accumulation steps: 1 |
|
|
|
### Framework versions |
|
|
|
- PEFT 0.4.0 |
|
|
|
### Loss metrics: |
|
 |
