Refactor MathWorkflows

[garyzhang99]

Description

As the title says.
This PR also enable training using base model, as the added BaseModelWorkflow shows.

Checklist

Please check the following items before code is ready to be reviewed.

• Code has passed all tests
• Docstrings have been added/updated in Google Style
• Documentation has been updated
• Code is ready for review

[pan-x-c]

/run-unittest

[github-actions]

Summary

Tests 📝	Passed ✅	Failed ❌	Skipped ⏭️	Pending ⏳	Other ❓	Flaky 🍂	Duration ⏱️
25	25	0	0	0	0	0	847ms

Failed Tests

No failed tests ✨

Flaky Tests

No flaky tests ✨

Skipped

No skipped tests ✨

Tests

Test Name	Status	Flaky	Duration
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer	✅		4ms
tests/buffer/sql_test.py::TestSQLBuffer::test_create_sql_buffer	✅		1ms
tests/common/config_test.py::TestConfig::test_all_examples_are_valid	✅		1ms
tests/common/config_test.py::TestConfig::test_load_default_config	✅		5ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion	✅		1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion	✅		1ms
tests/common/vllm_test.py::TestModelWrapperSyncV0::test_generate	✅		44ms
tests/common/vllm_test.py::TestModelWrapperAsyncV0::test_generate	✅		43ms
tests/common/vllm_test.py::TestModelWrapperAsyncTPV0::test_generate	✅		52ms
tests/common/vllm_test.py::TestModelWrapperAsyncTPV1::test_generate	✅		53ms
tests/common/vllm_test.py::TestModelWrapperAsyncV1::test_generate	✅		40ms
tests/common/vllm_test.py::TestAPIServer::test_api	✅		22ms
tests/common/vllm_test.py::TestTokenizer::test_assistant_token_mask	✅		1ms
tests/explorer/explorer_test.py::BaseExplorerCase::test_explorer	✅		1ms
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer	✅		123ms
tests/explorer/explorer_test.py::TestExplorerCountdownNoEval::test_explorer	✅		129ms
tests/explorer/runner_pool_test.py::RunnerPoolTest::test_runner_pool	✅		19ms
tests/explorer/runner_pool_test.py::RunnerPoolTest::test_runner_pool_with_auxiliary_models	✅		3ms
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow	✅		1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow	✅		1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow	✅		1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow	✅		1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow_with_different_system_prompt	✅		1ms
tests/trainer/trainer_test.py::BaseTrainerCase::test_trainer	✅		1ms
tests/trainer/trainer_test.py::TestTrainerCountdown::test_trainer	✅		295ms

Github Test Reporter by CTRF 💚

[pan-x-c]

The system_prompt here is a bit confusing

[garyzhang99]

It is basically the same as the old MathWorkflow. Any recommendation on how to improve it?

[pan-x-c]

We should add a workflow_args: Dict field to the __init__ method of Workflow interface