Zangs3011's picture
Librarian Bot: Add base_model information to model (#1)
11ecddb
metadata
library_name: peft
tags:
  - llama2-7b
  - code
  - instruct
  - instruct-code
  - code-alpaca
  - alpaca-instruct
  - alpaca
  - llama7b
  - gpt2
datasets:
  - sahil2801/CodeAlpaca-20k
base_model: meta-llama/Llama-2-7b-hf

We finetuned Llama2-7B on Code-Alpaca-Instruct Dataset (sahil2801/CodeAlpaca-20k) for 5 epochs or ~ 25,000 steps using MonsterAPI no-code LLM finetuner.

This dataset is HuggingFaceH4/CodeAlpaca_20K unfiltered, removing 36 instances of blatant alignment.

The finetuning session got completed in 4 hours and costed us only $16 for the entire finetuning run!

Hyperparameters & Run details:

  • Model Path: meta-llama/Llama-2-7b
  • Dataset: sahil2801/CodeAlpaca-20k
  • Learning rate: 0.0003
  • Number of epochs: 5
  • Data split: Training: 90% / Validation: 10%
  • Gradient accumulation steps: 1

Loss metrics: training loss


license: apache-2.0