---
license: apache-2.0
library_name: peft
tags:
- falcon
- falcon-7b
- code
- code instruct
- instruct code
- code alpaca
- python code
- code copilot
- copilot
- python coding assistant
- coding assistant
datasets:
- iamtarun/python_code_instructions_18k_alpaca
base_model: tiiuae/falcon-7b
---
## Training procedure
We finetuned Falcon-7B LLM on Python-Code-Instructions Dataset ([iamtarun/python_code_instructions_18k_alpaca](https://huggingface.co/datasets/iamtarun/python_code_instructions_18k_alpaca)) for 10 epochs or ~ 23,000 steps using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).

The dataset contains problem descriptions and code in python language. This dataset is taken from sahil2801/code_instructions_120k, which adds a prompt column in alpaca style. 

The finetuning session got completed in 7.3  hours and costed us only `$17.5` for the entire finetuning run!

#### Hyperparameters & Run details:
- Model Path: tiiuae/falcon-7b
- Dataset: iamtarun/python_code_instructions_18k_alpaca
- Learning rate: 0.0002
- Number of epochs: 10
- Data split: Training: 95% / Validation: 5%
- Gradient accumulation steps: 1



### Framework versions

- PEFT 0.4.0

### Loss metrics:
![training loss](train-loss.png "Training loss")