GH Task Runner (Large Suite) #140
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: GH Task Runner (Large Suite) | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| approval_notice: | |
| description: 'WARNING: This will spin up a large number of tasks - get approval from admin before running' | |
| required: false | |
| default: 'NOT_APPROVED' | |
| type: choice | |
| options: | |
| - NOT_APPROVED | |
| - APPROVED | |
| model_hf_repo: | |
| description: 'Model Hugging Face Repository' | |
| required: true | |
| default: 'RWKV/rwkv-5-world-1b5' | |
| model_args: | |
| description: 'Model Arguments (ie: dtype="float16")' | |
| required: false | |
| default: 'dtype=bfloat16,trust_remote_code=True' | |
| batch_size: | |
| description: 'Batch Size' | |
| required: true | |
| default: 'auto' | |
| # backend: | |
| # description: 'Backend to use' | |
| # required: true | |
| # default: 'nvidia-gpu' | |
| # type: choice | |
| # options: | |
| # - nvidia-gpu | |
| # - intel-gpu | |
| # - amd-gpu | |
| # - any-gpu | |
| gpu_vram: | |
| description: 'Minimum GPU VRAM (ignored for MPS)' | |
| required: true | |
| default: '24' | |
| type: choice | |
| options: | |
| - 16 | |
| - 24 | |
| # - 40 | |
| - 48 | |
| - 80 | |
| rwkv5_file_url: | |
| description: 'Model file URL (for rwkv5 .pth eval)' | |
| default: '' | |
| required: false | |
| rwkv5_test_name: | |
| description: 'Model dev test name (for test)' | |
| default: 'TEST_MODEL_FILE' | |
| required: false | |
| num_fewshot: | |
| description: 'num_fewshot setting (ignored if < 0)' | |
| required: true | |
| default: -1 | |
| upload_output: | |
| description: 'Upload to HF / B2' | |
| required: false | |
| default: true | |
| type: boolean | |
| env: | |
| # Get the final task | |
| RUN_TASK: ${{ github.event.inputs.custom_task || github.event.inputs.run_task }} | |
| # HF repo to sync to | |
| HF_REPO_SYNC: rwkv-x-dev/lm-eval-output | |
| # Model HF repo | |
| MODEL_HF_REPO: ${{ github.event.inputs.model_hf_repo }} | |
| # HF / B2 sync settings | |
| HUGGING_FACE_HUB_TOKEN: ${{secrets.HUGGING_FACE_HUB_TOKEN}} | |
| B2_APPLICATION_KEY_ID: ${{secrets.B2_APPLICATION_KEY_ID}} | |
| B2_APPLICATION_KEY: ${{secrets.B2_APPLICATION_KEY}} | |
| B2_PATH_LM_EVAL_OUTPUT: ${{vars.B2_PATH_LM_EVAL_OUTPUT}} | |
| jobs: | |
| gh-task-runner: | |
| # Check for approval notice | |
| if: ${{ github.event.inputs.approval_notice == 'APPROVED' }} | |
| # Strategy Matrix | |
| strategy: | |
| # Disable fail-fast behavior | |
| fail-fast: false | |
| matrix: | |
| # NOTE: There is a matrix limit of 256 on github | |
| run_task: | |
| ### Large task collection, which overlaps with existing tasks | |
| ### ---------------------------------------------------------------------------- | |
| # - multiple_choice | |
| # - loglikelihood | |
| ### Medium Slow tasks (>=15 mins on 4x3090) | |
| ### ---------------------------------------------------------------------------- | |
| - glue | |
| # - gsm8k | |
| - kmmlu | |
| - qqp | |
| - pythia | |
| # - kmmlu_* | |
| ### Faster tasks (<= 15 mins on 4x3090) | |
| ### ---------------------------------------------------------------------------- | |
| - arithmetic_* | |
| - asdiv | |
| - anli | |
| # - anli_* | |
| - ai2_arc | |
| # - arc_easy | |
| # - arc_challenge | |
| - arithmetic | |
| - blimp | |
| # - blimp_* | |
| - boolq | |
| - cb | |
| - ceval-valid | |
| # - ceval-valid_* | |
| - cmmlu | |
| # - cmmlu_* | |
| - cola | |
| - copa | |
| - crows_pairs | |
| # - crows_pairs_* | |
| - freebase | |
| - hellaswag | |
| - kobest | |
| # - kobest_* | |
| - lambada | |
| - lambada_cloze | |
| # - lambada_* | |
| - logieval | |
| - logiqa | |
| - logiqa2 | |
| - mathqa | |
| - mc_taco | |
| - medmcqa | |
| - medqa_4options | |
| - mmlu | |
| # - mmlu_* | |
| - mnli | |
| - mnli_mismatch | |
| - mrpc | |
| - multimedqa | |
| - multirc | |
| - mutual | |
| - mutual_plus | |
| - openbookqa | |
| - piqa | |
| - prost | |
| - pubmedqa | |
| - qa4mre | |
| # - qa4mre_* | |
| - qnli | |
| - race | |
| - rte | |
| - sciq | |
| - sglue_rte | |
| - sst2 | |
| - swag | |
| - sycophancy | |
| # - sycophancy_on_* | |
| - truthfulqa | |
| # - truthfulqa_* | |
| - webqs | |
| - wic | |
| - wikitext | |
| - winogrande | |
| - wnli | |
| - wsc | |
| - wsc273 | |
| # Name of the job | |
| name: "[${{ matrix.run_task }}] ${{ github.event.inputs.rwkv5_file_url && github.event.inputs.rwkv5_test_name || github.event.inputs.model_hf_repo }} - ${{ github.event.inputs.model_args }}" | |
| # Due to github worker hard limitation, of 24 hours | |
| # we apply a timeout of 23 hours instead. | |
| timeout-minutes: 1380 | |
| # Select the type of runner that the job will run on | |
| runs-on: | |
| - nvidia-gpu | |
| - gpu-vram-${{ github.event.inputs.gpu_vram }} | |
| # - gpu-count-any | |
| # Actual task setup, and run steps | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v3 | |
| - name: Run the task | |
| uses: ./.github/actions/gh-task-runner-composite | |
| with: | |
| run_task: ${{ matrix.run_task }} | |
| num_fewshot: ${{ github.event.inputs.num_fewshot }} | |
| model_hf_repo: ${{ github.event.inputs.model_hf_repo }} | |
| model_args: ${{ github.event.inputs.model_args }} | |
| batch_size: ${{ github.event.inputs.batch_size }} | |
| rwkv5_file_url: ${{ github.event.inputs.rwkv5_file_url }} | |
| rwkv5_test_name: ${{ github.event.inputs.rwkv5_test_name }} | |
| upload_output: ${{ github.event.inputs.upload_output }} | |
| # upload_output: | |
| # name: "Upload to HF / B2" | |
| # needs: gh-task-runner | |
| # runs-on: ubuntu-latest | |
| # if: ${{ github.event.inputs.upload_output }} | |
| # steps: | |
| # - name: Checkout repository | |
| # uses: actions/checkout@v3 | |
| # - name: Run the task | |
| # uses: ./.github/actions/gh-upload-output | |
| # with: | |
| # num_fewshot: ${{ github.event.inputs.num_fewshot }} | |
| # model_hf_repo: ${{ github.event.inputs.model_hf_repo }} | |
| # model_args: ${{ github.event.inputs.model_args }} | |
| # batch_size: ${{ github.event.inputs.batch_size }} | |
| # backend: nvidia-gpu | |