Add a callback to write huggingface checkpoints during the training r… #172

	name: Docker
	on:
	push:
	branches:
	- main
	workflow_dispatch: {}
	jobs:
	docker-build:
	runs-on: ubuntu-latest
	if: github.repository_owner == 'mosaicml'
	strategy:
	matrix:
	include:
	- name: '1.13.1_cu117'
	base_image: mosaicml/pytorch:1.13.1_cu117-python3.10-ubuntu20.04
	- name: '2.0.1_cu118'
	base_image: mosaicml/pytorch:2.0.1_cu118-python3.10-ubuntu20.04

	steps:
	- name: Maximize Build Space on Worker
	uses: easimon/maximize-build-space@v4
	with:
	overprovision-lvm: true
	remove-dotnet: true
	remove-android: true
	remove-haskell: true

	- name: Checkout
	uses: actions/checkout@v3

	- name: Setup QEMU
	uses: docker/setup-qemu-action@v2

	- name: Setup Docker Buildx
	uses: docker/setup-buildx-action@v2

	- name: Login to DockerHub
	uses: docker/login-action@v2
	with:
	username: ${{ secrets.DOCKER_HUB_USERNAME }}
	password: ${{ secrets.DOCKER_HUB_PASSWORD }}

	- name: Calculate Docker Image Variables
	run: \|
	set -euxo pipefail

	###################
	# Calculate the tag
	###################
	GIT_SHA=$(echo ${{ github.sha }} \| cut -c1-7)
	echo "IMAGE_TAG=${GIT_SHA}" >> ${GITHUB_ENV}

	- name: Build and Push the Docker Image
	uses: docker/build-push-action@v3
	with:
	context: .
	tags: mosaicml/llm-foundry:${{ matrix.name }}-latest,
	mosaicml/llm-foundry:${{ matrix.name }}-${{ env.IMAGE_TAG }}
	push: true
	cache-from: type=registry,ref=mosaicml/llm-foundry:${{ matrix.name }}-buildcache
	cache-to: type=registry,ref=mosaicml/llm-foundry:${{ matrix.name }}-buildcache,mode=max
	build-args: BASE_IMAGE=${{ matrix.base_image }}

Provide feedback