368b19b237* Studio: derive training output dir from model basename for local-drive models A LoRA/QLoRA run started from a model loaded by absolute path (common when models live on a non-system drive, e.g. G:\modelsAI\...\gemma-4-12B-it) seeded the default output dir with that full path. resolve_output_dir then raised "path escapes root ... is not under the studio outputs folder", so training could not start from a model stored off the system drive. Add default_run_dir_name(): Hugging Face repo ids keep their namespace (org/model becomes org_model), while local paths collapse to their final component so an absolute source path can no longer leak into the output dir. Use it at the three worker derivation sites and add a regression test. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: cap run dir name length and drop redundant resolve Apply PR review feedback: length-cap the auto-generated output dir component so an unusually long model name stays under the filesystem name limit, and drop the redundant double resolve_output_dir at the embedding site so all three derivation sites match. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
65 lines
2.3 KiB
Python
65 lines
2.3 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""Auto-generated training output dir names stay inside outputs_root.
|
|
|
|
Regression for local-model training: a model loaded by absolute path (e.g.
|
|
``G:\\modelsAI\\...\\gemma-4-12B-it`` on a non-system drive) used to seed the
|
|
default run dir with that full path, so ``resolve_output_dir`` raised
|
|
``path escapes root`` because the result was not under ``<studio>/outputs``.
|
|
"""
|
|
|
|
import importlib.util
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
|
|
_BACKEND_DIR = Path(__file__).resolve().parent.parent
|
|
|
|
|
|
def _load_storage_roots():
|
|
path = _BACKEND_DIR / "utils/paths/storage_roots.py"
|
|
spec = importlib.util.spec_from_file_location("storage_roots_under_test", path)
|
|
module = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(module)
|
|
return module
|
|
|
|
|
|
def test_repo_id_keeps_namespace():
|
|
sr = _load_storage_roots()
|
|
assert sr.default_run_dir_name("unsloth/gemma-3-4b") == "unsloth_gemma-3-4b"
|
|
assert sr.default_run_dir_name("gemma-3-4b") == "gemma-3-4b"
|
|
|
|
|
|
def test_local_paths_collapse_to_basename():
|
|
sr = _load_storage_roots()
|
|
assert sr.default_run_dir_name(r"G:\modelsAI\gguf\test\gemma-4-12B-it") == "gemma-4-12B-it"
|
|
assert sr.default_run_dir_name("/data/models/gemma-3-4b") == "gemma-3-4b"
|
|
assert sr.default_run_dir_name("~/models/gemma-3-4b") == "gemma-3-4b"
|
|
assert sr.default_run_dir_name("C:/Users/me/models/gemma-3-4b") == "gemma-3-4b"
|
|
|
|
|
|
def test_empty_falls_back_to_model():
|
|
sr = _load_storage_roots()
|
|
assert sr.default_run_dir_name("") == "model"
|
|
assert sr.default_run_dir_name(" ") == "model"
|
|
|
|
|
|
def test_very_long_name_is_capped():
|
|
sr = _load_storage_roots()
|
|
name = sr.default_run_dir_name("a" * 500)
|
|
assert 0 < len(name) <= 200
|
|
|
|
|
|
def test_derived_name_resolves_under_outputs_root(tmp_path, monkeypatch):
|
|
sr = _load_storage_roots()
|
|
outputs = tmp_path / "outputs"
|
|
outputs.mkdir()
|
|
monkeypatch.setattr(sr, "outputs_root", lambda: outputs)
|
|
|
|
name = sr.default_run_dir_name(r"G:\modelsAI\gguf\test\gemma-4-12B-it")
|
|
resolved = sr.resolve_output_dir(f"{name}_1781327234")
|
|
assert resolved == outputs / "gemma-4-12B-it_1781327234"
|
|
# No escape: the absolute G: source no longer leaks into the output path.
|
|
assert "modelsAI" not in str(resolved)
|