add miniPile dataset for pretraining, 1M entries (solves the 'out of data' at 40 iters issue) #20

	name: 4 GPU Unit Test

	on:
	push:
	branches: [ main ]
	pull_request:

	concurrency:
	group: unit-test${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_number \|\| github.ref }}
	cancel-in-progress: true

	defaults:
	run:
	shell: bash -l -eo pipefail {0}

	jobs:
	unit_tests_4gpu:
	runs-on: linux.g5.12xlarge.nvidia.gpu
	strategy:
	matrix:
	python-version: ['3.10']
	steps:
	- name: Check out repo
	uses: actions/checkout@v3
	- name: Setup conda env
	uses: conda-incubator/setup-miniconda@v2
	with:
	auto-update-conda: true
	miniconda-version: "latest"
	activate-environment: test
	python-version: ${{ matrix.python-version }}
	- name: Update pip
	run: python -m pip install --upgrade pip
	- name: Install dependencies
	run: \|
	pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121
	python -m pip install -r requirements.txt
	python -m pip install -r dev-requirements.txt
	python -m pip install -e .
	- name: Run NGPU=4 ./run_llama_train.sh
	run: NGPU=4 ./run_llama_train.sh
	- name: Upload Coverage to Codecov
	uses: codecov/codecov-action@v3

Provide feedback