Skip to content

Conversation

@pan-x-c
Copy link
Collaborator

@pan-x-c pan-x-c commented Nov 11, 2025

Description

Note

Experimental feature. The inferface may change in future versions.

This PR introduces "Over Rollout", which submitting n tasks at each step, but only waiting for 1 - over_rollout_rate of them to return.

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

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @pan-x-c, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request implements an experimental 'Over Rollout' feature designed to optimize task execution by submitting more tasks than are strictly necessary, and then waiting for a subset of them to complete. This involves a substantial overhaul of the task scheduling and execution logic, including how tasks are managed, metrics are collected and aggregated, and results are processed. The changes are supported by new configuration options and comprehensive unit tests to ensure the feature's correctness and compatibility.

Highlights

  • New Feature: Over Rollout: Introduces an experimental 'Over Rollout' mechanism where n tasks are submitted, but the system only waits for 1 - over_rollout_rate of them to complete. This aims to improve efficiency by allowing more tasks to be processed concurrently than strictly required for a batch.
  • Enhanced Metric Collection and Aggregation: The Status object now stores a list of metrics, allowing for more granular collection of run-level and task-level metrics. New utility functions (calculate_task_level_metrics, calculate_run_level_metrics) have been added to aggregate these metrics.
  • Scheduler and Workflow Runner Refactoring: Significant changes were made to Scheduler and WorkflowRunner to support the new over rollout logic, including modifications to TaskWrapper for sub-task tracking, updated run_with_retry methods, and adjustments to how tasks are split and results are collected.
  • Configuration and Validation: A new over_rollout_rate field has been added to ExplorerConfig, along with validation to ensure it's within [0.0, 1.0) and is not used with a FIXED synchronization style.
  • New Test Cases: Added new test cases in scheduler_test.py to verify metric calculation for both repeatable and non-repeatable workflows, and a dedicated TestOverRollout class in trainer_test.py to validate the end-to-end functionality of the over rollout feature.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces an experimental "Over Rollout" feature, which is a valuable optimization for handling straggler tasks during exploration. The implementation includes a significant and well-executed refactoring of the scheduler and workflow runner to manage task splitting and result aggregation. The approach to calculating and propagating metrics has also been enhanced. My review focuses on identifying a bug in the new tests, suggesting simplifications to reduce code complexity and duplication, and correcting minor inconsistencies to improve overall code quality.

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 11, 2025

/unittest-all

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 11, 2025

/unittest-module-explorer

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 11, 2025

/unittest-module-explorer

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 11, 2025

/unittest-module-trainer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
40 39 0 1 0 0 13m 5s

Skipped

Tests Status
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 1m 20s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 37s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 37s
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 24s
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 12.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 12.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 27.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 12.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 12.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 12.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 12.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 12.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 12.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 22.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 23.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 15.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 32.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 15.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 21.0s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_1 602ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_0 2ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_1 1.0s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_raise_error 3ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_stop_at_max_env_steps 1.0s
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow 33ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 24ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 173ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 3ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 13ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 8ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 85ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 101ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 201ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 15.2s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 15.6s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter ⏭️ 1ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 291ms

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 12, 2025

/unittest-module-trainer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
21 19 0 2 0 0 40m 42s

Skipped

Tests Status
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 2m 56s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 4m 57s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 18s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 17s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 18s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 22s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 32s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 2m 25s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 1m
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 57.8s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 57.8s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 47s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 56s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 53s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 11s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 39s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 1m 27s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 809ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 809ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 3m 15s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 10s

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c changed the title [WIP] Support Over Rollout Support Over Rollout Nov 12, 2025
@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 12, 2025

/unittest-module-explorer

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 12, 2025

/unittest-module-trainer

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 12, 2025

/unittest-diff

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
76 75 0 1 0 0 18m 22s

Skipped

Tests Status
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 32.8s
tests/common/config_test.py::TestConfig::test_config_flatten 40ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 187ms
tests/common/config_test.py::TestConfig::test_default_workflow 89ms
tests/common/config_test.py::TestConfig::test_load_default_config 3.6s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 91ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 89ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 1.9s
tests/common/experience_test.py::TestEID::test_eid_properties 1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type 1ms
tests/common/experience_test.py::TestExperience::test_assertions 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience 1ms
tests/common/experience_test.py::TestExperience::test_gather 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion 15ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize 2ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_to_dict 1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_gather_experiences_with_custom_fields 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 52.1s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 32.4s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 42.1s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 17.2s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 16.9s
tests/common/vllm_test.py::TestAPIServer::test_api 22.5s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 22.4s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 262ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 255ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 19.4s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 17.7s
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 1m 17s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 43s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 38s
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 21s
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 13.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 12.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 19.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 27.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 12.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 12.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 12.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 12.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 12.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 12.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 16.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 22.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 24.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 15.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 32.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 15.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 21.1s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 2ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_1 602ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_1 1.0s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_raise_error 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_stop_at_max_env_steps 1.0s
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow 34ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 24ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 175ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 4ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 13ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 8ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 88ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 101ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 201ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 14.3s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 14.6s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter ⏭️ 1ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 298ms

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 13, 2025

/unittest-all

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
180 176 1 3 0 0 1h 16m

Failed Tests

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

Skipped

Tests Status
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_std_grpo 40ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_step_wise_grpo_advantage 2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_duplicate_grpo 5ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_advantage 3ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_correct_bias 2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_reward_std 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_advantage 2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_with_std_threshold 2ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_dpo_policy_loss 2ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_gspo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_mix_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_opmd_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_ppo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_sft_policy_loss 1ms
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_experience_pipeline 19.1s
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_pass_rate_calculation 15.2s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 3.9s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_0_sft 6.1s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_1_dpo 6.5s
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 157ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 4.2s
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 537ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 505ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 825ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 1.0s
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 726ms
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 224ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 8.7s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 4.7s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_reuse_count_control 6.8s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_0_queue 5.9s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 5.9s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 6.1s
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 5ms
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_buffer_read_write 4.6s
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_0 179ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_1 159ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_2 159ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_3 164ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_4 179ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0 69ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_1 3.9s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_2 49ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3 4.2s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4 49ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5 4.7s
tests/cli/launcher_test.py::TestLauncherMain::test_debug_mode 46.3s
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_command 6.5s
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_in_dlc 1.5s
tests/cli/launcher_test.py::TestLauncherMain::test_main_studio_command 313ms
tests/cli/launcher_test.py::TestLauncherMain::test_multi_stage_run 1.8s
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 32.9s
tests/common/config_test.py::TestConfig::test_config_flatten 40ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 187ms
tests/common/config_test.py::TestConfig::test_default_workflow 88ms
tests/common/config_test.py::TestConfig::test_load_default_config 3.2s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 92ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 90ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 153ms
tests/common/experience_test.py::TestEID::test_eid_properties 1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type 1ms
tests/common/experience_test.py::TestExperience::test_assertions 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience 1ms
tests/common/experience_test.py::TestExperience::test_gather 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion 14ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize 1ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_to_dict 1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_gather_experiences_with_custom_fields 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 45.7s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 31.7s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 43.5s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 17.1s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 16.9s
tests/common/vllm_test.py::TestAPIServer::test_api 23.0s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 22.6s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 241ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 227ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 19.7s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 17.9s
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 1m 5s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 42s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 37s
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 21s
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 12.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 12.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 19.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 27.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 13.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 12.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 12.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 12.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 12.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 12.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 16.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 22.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 23.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 15.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 32.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 15.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 21.4s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 2ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_1 602ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_1 1.0s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_raise_error 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_stop_at_max_env_steps 1.0s
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow 15ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 24ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 267ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 4ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 16ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 10ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 83ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 101ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 201ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 14.6s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 14.7s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter ⏭️ 1ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 299ms
tests/manager/synchronizer_test.py::TestSynchronizerExit::test_synchronizer 60.0s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_0::test_synchronizer 1m 43s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_1::test_synchronizer 1m 46s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_2::test_synchronizer 2m 31s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_3::test_synchronizer 2m 30s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_0::test_synchronizer 1m 44s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_1::test_synchronizer 1m 44s
tests/service/data_juicer_test.py::TestDataJuicer::test_config 1.4s
tests/service/data_juicer_test.py::TestDataJuicer::test_server_start 21.6s
tests/service/data_juicer_test.py::TestDataJuicerExperiencePipeline::test_data_juicer_operators 31.4s
tests/service/data_juicer_test.py::TestDataJuicerTaskPipeline::test_data_juicer_task_pipeline 14.4s
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 2m 59s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 23s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 21s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 20s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 22s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 29s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 2m 23s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 1m 1s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 57.7s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 57.3s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 53s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 48s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 55s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 15s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 35s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 1m 26s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 816ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 809ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 2m 58s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 14s
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_equivalent 15ms
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_not_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_empty_ground_truth 2ms
tests/utils/eval_utils_test.py::TestComputeScore::test_empty_solution_string 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_multiple_boxed_answers_in_solution 2ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_boxed_truth_raw_and_equivalent 3ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_boxed_truth_raw_and_not_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_not_boxed 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_raw_and_ground_truth_boxed_equivalent 1ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_extract_answer 4ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_verify_math_answer 75ms
tests/utils/eval_utils_test.py::TestEvalUtils::test_is_equiv 6ms
tests/utils/log_test.py::LogTest::test_actor_log 5.0s
tests/utils/log_test.py::LogTest::test_group_by_node 4.9s
tests/utils/log_test.py::LogTest::test_no_actor_log 901ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local_0__workspace_tests_utils_plugins 92ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local_1_tests_utils_plugins 91ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote_0__workspace_tests_utils_plugins 21.9s
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote_1_tests_utils_plugins 22.0s
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class_0__workspace_tests_utils_plugins 11.8s
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class_1_tests_utils_plugins 11.4s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 13, 2025

/unittest-module-trainer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
21 18 1 2 0 0 40m 22s

Failed Tests

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

Skipped

Tests Status
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 2m 49s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 10s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 31s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 20s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 18s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 22s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 34s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 2m 28s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 1m
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 57.0s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 56.8s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 51s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 49s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 55s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 16s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 36s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 1m 19s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 810ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 809ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 2m 36s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 11s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 19, 2025

/unittest-module-trainer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
21 18 1 2 0 0 40m 7s

Failed Tests

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

Skipped

Tests Status
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 3m 6s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 3s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 25s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 16s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 20s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 19s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 30s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 2m 23s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 1m 1s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 57.7s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 57.8s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 47s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 49s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 54s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 11s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 29s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 1m 21s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 809ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 809ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 2m 45s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 11s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Nov 19, 2025

/unittest-module-trainer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
21 19 0 2 0 0 40m 50s

Skipped

Tests Status
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 2m 50s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 3s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 26s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 22s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 20s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 22s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 30s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 2m 22s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 1m 1s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 57.2s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 57.7s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 52s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 47s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 57s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 13s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 54s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 1m 22s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 608ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 807ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 3m 3s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 9s

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c merged commit 1de31a6 into modelscope:main Nov 20, 2025
2 checks 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.

3 participants