HarborTask
One RL task - instruction + verifier spec.
Same shape whether the task came from a hand-written eval set, an HF
dataset, or a generated rollout corpus. Runners materialize the prompt by
feeding instruction to the policy, generate a rollout, and score it
using verifier (whichever variant - see VerifierPayload).
Attributes
attributetask_idstrattributeinstructionstrattributeverifierVerifierPayloadattributemetadatadict= field(default_factory=dict)Functions
func__init__(self, task_id, instruction, verifier, metadata=dict()) -> Noneparamselfparamtask_idstrparaminstructionstrparamverifierVerifierPayloadparammetadatadict= dict()Returns
None