axolotl-spot.yaml

# Usage:
#
#  Unmanaged spot (no auto-recovery; for debugging):
#   HF_TOKEN=abc BUCKET=<unique-name> sky launch -c axolotl-spot axolotl-spot.yaml --env HF_TOKEN --env BUCKET -i30 --down
#
#  Managed spot (auto-recovery; for full runs):
#   HF_TOKEN=abc BUCKET=<unique-name> sky spot launch -n axolotl-spot axolotl-spot.yaml --env HF_TOKEN --env BUCKET

name: axolotl

resources:
  accelerators: A100:1
  cloud: gcp # optional
  use_spot: True
  image_id: docker:winglian/axolotl:main-py3.10-cu118-2.0.1

workdir: mistral

file_mounts:
  /sky-notebook:
    name: ${BUCKET}
    mode: MOUNT

run: |
  huggingface-cli login --token ${HF_TOKEN}
  
  accelerate launch -m axolotl.cli.train qlora-checkpoint.yaml

envs:
  HF_TOKEN: # TODO: Fill with your own huggingface token, or use --env to pass.
  BUCKET: # TODO: Fill with your unique bucket name, or use --env to pass.

4