mirror of
https://github.com/microsoft/SkillOpt.git
synced 2026-07-08 08:59:22 +08:00
98d0430bee
All six adapters duplicated an identical reflect() that delegates to run_minibatch_reflect. The copies had drifted: OfficeQA/DocVQA silently dropped meta_skill_context and ALFWorld dropped update_mode, so those analysts ran without inputs every other benchmark receives (active under the default use_meta_skill: true). Move the delegation into EnvAdapter.reflect as one default that forwards all kwargs uniformly, and delete the six overrides. reflect is no longer abstract — adapters inherit it and override only for custom logic. Net -225 lines. Behavior change: OfficeQA/DocVQA/ALFWorld reflect now receive the kwargs they previously dropped; the three already-correct benchmarks are unaffected. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
91 lines
3.3 KiB
Python
91 lines
3.3 KiB
Python
from __future__ import annotations
|
|
|
|
from skillopt.datasets.base import BatchSpec
|
|
from skillopt.envs.base import EnvAdapter
|
|
from skillopt.envs.docvqa.dataloader import DocVQADataLoader
|
|
from skillopt.envs.docvqa.rollout import run_batch
|
|
|
|
|
|
class DocVQAAdapter(EnvAdapter):
|
|
def __init__(
|
|
self,
|
|
split_dir: str = "",
|
|
data_path: str = "",
|
|
split_mode: str = "split_dir",
|
|
split_ratio: str = "2:1:7",
|
|
split_seed: int = 42,
|
|
split_output_dir: str = "",
|
|
max_turns: int = 1,
|
|
exec_timeout: int = 120,
|
|
workers: int = 16,
|
|
analyst_workers: int = 16,
|
|
failure_only: bool = False,
|
|
minibatch_size: int = 8,
|
|
edit_budget: int = 4,
|
|
seed: int = 42,
|
|
limit: int = 0,
|
|
image_detail: str = "auto",
|
|
max_completion_tokens: int = 16384,
|
|
) -> None:
|
|
self.max_turns = max_turns
|
|
self.exec_timeout = exec_timeout
|
|
self.workers = workers
|
|
self.max_completion_tokens = int(max_completion_tokens)
|
|
self.analyst_workers = analyst_workers
|
|
self.failure_only = failure_only
|
|
self.minibatch_size = minibatch_size
|
|
self.edit_budget = edit_budget
|
|
self.image_detail = image_detail
|
|
self.dataloader = DocVQADataLoader(
|
|
split_dir=split_dir,
|
|
data_path=data_path,
|
|
split_mode=split_mode,
|
|
split_ratio=split_ratio,
|
|
split_seed=split_seed,
|
|
split_output_dir=split_output_dir,
|
|
seed=seed,
|
|
limit=limit,
|
|
)
|
|
|
|
def setup(self, cfg: dict) -> None:
|
|
super().setup(cfg)
|
|
self.dataloader.setup(cfg)
|
|
|
|
def get_dataloader(self):
|
|
return self.dataloader
|
|
|
|
def build_env_from_batch(self, batch: BatchSpec, **kwargs):
|
|
return list(batch.payload or [])
|
|
|
|
def build_train_env(self, batch_size: int, seed: int, **kwargs):
|
|
batch = self.dataloader.build_train_batch(batch_size=batch_size, seed=seed, **kwargs)
|
|
return self.build_env_from_batch(batch, **kwargs)
|
|
|
|
def build_eval_env(self, env_num: int, split: str, seed: int, **kwargs):
|
|
batch = self.dataloader.build_eval_batch(env_num=env_num, split=split, seed=seed, **kwargs)
|
|
return self.build_env_from_batch(batch, **kwargs)
|
|
|
|
def rollout(self, env_manager, skill_content: str, out_dir: str, **kwargs) -> list[dict]:
|
|
items: list[dict] = env_manager
|
|
return run_batch(
|
|
items=items,
|
|
out_root=out_dir,
|
|
skill_content=skill_content,
|
|
max_turns=self.max_turns,
|
|
exec_timeout=self.exec_timeout,
|
|
workers=self.workers,
|
|
image_detail=self.image_detail,
|
|
max_completion_tokens=self.max_completion_tokens,
|
|
diagnostic_mode=kwargs.get("diagnostic_mode", False),
|
|
diagnostic_instruction=kwargs.get("diagnostic_instruction", ""),
|
|
task_timeout=self.exec_timeout,
|
|
)
|
|
|
|
def get_task_types(self) -> list[str]:
|
|
seen: list[str] = []
|
|
for item in self.dataloader.train_items + self.dataloader.val_items + self.dataloader.test_items:
|
|
task_type = str(item.get("task_type") or "docvqa")
|
|
if task_type not in seen:
|
|
seen.append(task_type)
|
|
return seen or ["docvqa"]
|