Add workflow to run evaluation for chronos-bolt-tiny on a subset of datasets #4

	# Evaluates Chronos-Bolt (Tiny) Model on Some Datasets
	name: Evaluate

	on:
	pull_request:
	branches: ["**"] # Run on any branch

	jobs:
	evaluate-and-post:
	if: contains(github.event.pull_request.labels.*.name, 'run-eval') # Only run if 'run-eval' label is added
	runs-on: ubuntu-latest

	steps:
	- name: Checkout Repository
	uses: actions/checkout@v4

	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: '3.11'

	- name: Install Dependencies
	run: pip install ".[evaluation]" -f https://download.pytorch.org/whl/cpu/torch_stable.html

	- name: Run Eval Script
	run: python scripts/evaluation/evaluate.py ci/evaluate/backtest_config.yaml eval-ci-metrics.csv --chronos-model-id=amazon/chronos-bolt-tiny --device=cpu --torch-dtype=float32

	- name: Read CSV
	id: csv
	uses: juliangruber/read-file-action@v1
	with:
	path: eval-ci-metrics.csv

	- name: Create Markdown Table
	uses: petems/csv-to-md-table-action@master
	id: csv-table-output
	with:
	csvinput: ${{ steps.csv.outputs.content }}

	- name: Post Table as a Comment
	uses: peter-evans/create-or-update-comment@v4
	with:
	token: ${{ secrets.PR_COMMENT_TOKEN }}
	repository: ${{ github.repository }}
	issue-number: ${{ github.event.pull_request.number }}
	body: \|
	### Evaluation Metrics
	${{steps.csv-table-output.outputs.markdown-table}}

Provide feedback