github/microsoft-SkillOpt
1
0
Fork 0
mirror of https://github.com/microsoft/SkillOpt.git synced 2026-07-03 14:02:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: align benchmark guide and template with dataloader.py naming

Browse Source 
The new-benchmark guide and the env template README referred to the data
loader file as loader.py, but all six built-in benchmarks name it
dataloader.py (skillopt/envs/<name>/dataloader.py). Update the docs and
the template rename step to match the actual convention.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Shunsuke
2026-06-09 12:20:01 +08:00
parent f64a41397c
commit 54e4b3eafb
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/guide/new-benchmark.md
View File

@@ -36,7 +36,7 @@ touch skillopt/envs/docfaithful/__init__.py
## Step 2 — Implement the data loader
`skillopt/envs/docfaithful/loader.py`:
`skillopt/envs/docfaithful/dataloader.py`:
```python
from __future__ import annotations
@@ -165,7 +165,7 @@ import os
from skillopt.datasets.base import BatchSpec
from skillopt.envs.base import EnvAdapter
from skillopt.envs.docfaithful.loader import DocFaithfulDataLoader
from skillopt.envs.docfaithful.dataloader import DocFaithfulDataLoader
from skillopt.envs.docfaithful.rollout import run_batch
from skillopt.gradient.reflect import run_minibatch_reflect

4
skillopt/envs/_template/README.md
View File

@@ -21,14 +21,14 @@ This directory provides scaffold files for adding a new benchmark to SkillOpt.
```bash
cd skillopt/envs/your_benchmark
mv env_template.py adapter.py
mv loader_template.py loader.py
mv loader_template.py dataloader.py
```
…and inside each file rename the classes
(`TemplateBenchmarkEnv → YourBenchmarkAdapter`,
`TemplateBenchmarkLoader → YourBenchmarkLoader`)
and fix the cross-import in `adapter.py`.
3. **Implement the TODO blocks** inside `adapter.py:rollout` and the
`_normalize_item` helper in `loader.py`. If you want real reflection,
`_normalize_item` helper in `dataloader.py`. If you want real reflection,
uncomment the `run_minibatch_reflect` block in `adapter.py:reflect`.
4. **Register** the adapter — add a `try / except ImportError` block in
`scripts/train.py`'s `_register_builtins()` mapping the registry key