(self)
| 256 | self.assertIn("I don't have a favorite color.", rejected) |
| 257 | |
| 258 | def test_task_formatter(self): |
| 259 | sample = { |
| 260 | "question": "1+1=", |
| 261 | "answer": "2", |
| 262 | "workflow": "math_rm_workflow", |
| 263 | "reward": "math_boxed_reward", |
| 264 | } |
| 265 | config = StorageConfig( |
| 266 | is_eval=True, |
| 267 | default_workflow_type="math_boxed_workflow", |
| 268 | workflow_args={"use_base": True, "with_think": True}, |
| 269 | ) |
| 270 | formatter = FORMATTER.get("task")(config=config) |
| 271 | task = formatter.format(sample) |
| 272 | from trinity.common.workflows.customized_math_workflows import MathBoxedWorkflow |
| 273 | |
| 274 | self.assertEqual(task.workflow, MathBoxedWorkflow) |
| 275 | self.assertTrue(task.workflow_args.get("use_base")) |
| 276 | self.assertTrue(task.workflow_args.get("with_think")) |
| 277 | self.assertEqual(task.raw_task, sample) |
| 278 | |
| 279 | config = StorageConfig( |
| 280 | is_eval=False, |
| 281 | default_workflow_type="math_workflow", |
| 282 | default_reward_fn_type="math_reward", |
| 283 | workflow_args={"use_base": False, "with_think": True}, |
| 284 | ) |
| 285 | formatter = FORMATTER.get("task")(config=config) |
| 286 | task = formatter.format(sample) |
| 287 | from trinity.common.rewards.math_reward import MathRewardFn |
| 288 | from trinity.common.workflows.workflow import MathWorkflow |
| 289 | |
| 290 | self.assertEqual(task.workflow, MathWorkflow) |
| 291 | self.assertEqual(task.reward_fn, MathRewardFn) |
| 292 | self.assertFalse(task.workflow_args.get("use_base")) |
| 293 | self.assertTrue(task.workflow_args.get("with_think")) |
| 294 | self.assertEqual(task.raw_task, sample) |
| 295 | |
| 296 | config = StorageConfig( |
| 297 | is_eval=False, |
| 298 | default_workflow_type="math_workflow", |
| 299 | workflow_args={"use_base": True, "with_think": False}, |
| 300 | format=FormatConfig( |
| 301 | workflow_key="workflow", |
| 302 | reward_fn_key="reward", |
| 303 | ), |
| 304 | ) |
| 305 | formatter = FORMATTER.get("task")(config=config) |
| 306 | task = formatter.format(sample) |
| 307 | from trinity.common.rewards.math_reward import MathBoxedRewardFn |
| 308 | from trinity.common.workflows.math_rm_workflow import MathRMWorkflow |
| 309 | |
| 310 | self.assertEqual(task.workflow, MathRMWorkflow) |
| 311 | self.assertEqual(task.reward_fn, MathBoxedRewardFn) |
| 312 | self.assertTrue(task.workflow_args.get("use_base")) |
| 313 | self.assertFalse(task.workflow_args.get("with_think")) |
| 314 | self.assertEqual(task.raw_task, sample) |
| 315 |
nothing calls this directly
no test coverage detected