evaluate-model #69

	name: "W&B Evaluate + Comparison Report"
	on:
	repository_dispatch:
	types: "evaluate-model"
	jobs:
	test:
	name: Evaluate + Report
	runs-on: ubuntu-latest
	env:
	WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }}
	steps:
	- name: Get current date
	id: date
	run: echo "TSTAMP=$(date +'%Y%m%d%H%M%S%N')" >> $GITHUB_ENV
	- uses: actions/checkout@v4
	- run: 'echo "payload: ${{ toJson(github.event.client_payload) }}"'
	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: '3.12.5'
	cache: 'pip'
	- name: Install Dependencies
	run: pip install -r ./requirements.txt
	- name: Login to W&B
	run: wandb login
	- name: Launch Job - candidate
	run: wandb launch -e reviewco -j "reviewco/eval-llama-3.1-8b-fine-tune/job-source-eval-llama-3.1-8b-fine-tune-evaluate_model.py:latest" --config '{"overrides":{"args":["${{env.TSTAMP}}", "candidate"]}}' -q "ReviewCo-Lambda-A10"
	- name: Launch Job - production
	run: wandb launch -e reviewco -j "reviewco/eval-llama-3.1-8b-fine-tune/job-source-eval-llama-3.1-8b-fine-tune-evaluate_model.py:latest" --config '{"overrides":{"args":["${{env.TSTAMP}}", "production"]}}' -q "ReviewCo-Lambda-A10"
	- name: Generate Evaluation Report
	run: python generate_report.py ${{env.TSTAMP}}
	- name: Inference Evaluation Deployment
	run: python inference_evaluation.py

Provide feedback