Skip to content

Conversation

@chenyushuo
Copy link
Collaborator

@chenyushuo chenyushuo commented Jun 4, 2025

Description

  1. Add unittest for GRPO, GRPO with SFT and DPO.
  2. Fix global_steps in verl_trainer.py.
  3. Set total_training_steps to config.trainer.total_training_steps for verl_trainer.py.
  4. Bug fix in SFT and DPO.

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

@chenyushuo
Copy link
Collaborator Author

/run-unittest

@pan-x-c
Copy link
Collaborator

pan-x-c commented Jun 4, 2025

/run-unittest

@github-actions
Copy link

github-actions bot commented Jun 4, 2025

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Pending ⏳ Other ❓ Flaky 🍂 Duration ⏱️
27 26 1 0 0 0 0 1.3s

Failed Tests

Failed Tests ❌ Fail Message
❌ tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer The test failed in the call phase due to an exception

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 45ms
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 128ms
tests/explorer/explorer_test.py::TestExplorerCountdownNoEval::test_explorer 132ms
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/trainer/trainer_test.py::BaseTrainerCase::test_trainer 1ms
tests/trainer/trainer_test.py::TestTrainerCountdown::test_trainer 440ms
tests/trainer/trainer_test.py::TestTrainerGSM8K::test_trainer 130ms
tests/trainer/trainer_test.py::TestTrainerGSM8KWithSFT::test_trainer 129ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 11ms

Github Test Reporter by CTRF 💚

@chenyushuo
Copy link
Collaborator Author

/run-unittest

@github-actions
Copy link

github-actions bot commented Jun 4, 2025

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Pending ⏳ Other ❓ Flaky 🍂 Duration ⏱️
27 27 0 0 0 0 0 1.4s

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 6ms
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 44ms
tests/common/vllm_test.py::TestModelWrapperAsyncTPV0::test_generate 52ms
tests/common/vllm_test.py::TestModelWrapperAsyncTPV1::test_generate 52ms
tests/common/vllm_test.py::TestModelWrapperAsyncV1::test_generate 39ms
tests/common/vllm_test.py::TestAPIServer::test_api 23ms
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 116ms
tests/explorer/explorer_test.py::TestExplorerCountdownNoEval::test_explorer 150ms
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/trainer/trainer_test.py::BaseTrainerCase::test_trainer 1ms
tests/trainer/trainer_test.py::TestTrainerCountdown::test_trainer 451ms
tests/trainer/trainer_test.py::TestTrainerGSM8K::test_trainer 122ms
tests/trainer/trainer_test.py::TestTrainerGSM8KWithSFT::test_trainer 123ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 119ms

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c merged commit 9d582e8 into modelscope:algorithm_dev Jun 4, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants