* Replace standalone Studio wording with Unsloth Replace the single word Studio with Unsloth wherever it is used as shorthand for Unsloth Studio in docs, CLI output, UI strings, i18n locales, workflow display names, comments and docstrings. Kept unchanged: the full name Unsloth Studio, third party product names (LM Studio, Visual Studio, Mac Studio), feature names (Recipe Studio, Fine-tuning Studio and its translations), and all identifiers such as env vars, commands, paths and filenames. * Address review feedback on the Studio wording rename Use "an" before Unsloth where the rename left the article as "a". Restore the split brand where Unsloth and Studio render as two halves of the full product name: the onboarding sidebar subtitle and the IPv6 localhost warning. Scope two messages to the full name Unsloth Studio where plain Unsloth was misleading: the AMD README bullet and the CLI studio setup error.
96 lines
2.7 KiB
Python
96 lines
2.7 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
|
|
|
|
"""Helpers for validating resumable training outputs."""
|
|
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Optional
|
|
|
|
from utils.paths import outputs_root, resolve_output_dir
|
|
|
|
|
|
def _is_under_outputs(path: Path) -> bool:
|
|
resolved = path.resolve(strict = False)
|
|
root = outputs_root().resolve(strict = False)
|
|
try:
|
|
resolved.relative_to(root)
|
|
return True
|
|
except ValueError:
|
|
return False
|
|
|
|
|
|
def has_resume_state(path_value: Optional[str]) -> bool:
|
|
if not path_value:
|
|
return False
|
|
return get_resume_checkpoint_path(path_value) is not None
|
|
|
|
|
|
def _checkpoint_step(path: Path) -> int:
|
|
try:
|
|
return int(path.name.removeprefix("checkpoint-"))
|
|
except ValueError:
|
|
return -1
|
|
|
|
|
|
def get_resume_checkpoint_path(path_value: str) -> Optional[str]:
|
|
path = resolve_output_dir(path_value)
|
|
if not _is_under_outputs(path) or not path.is_dir():
|
|
return None
|
|
if (path / "trainer_state.json").is_file():
|
|
return str(path)
|
|
|
|
checkpoints = [
|
|
child
|
|
for child in path.glob("checkpoint-*")
|
|
if child.is_dir() and (child / "trainer_state.json").is_file()
|
|
]
|
|
if not checkpoints:
|
|
return None
|
|
return str(max(checkpoints, key = _checkpoint_step))
|
|
|
|
|
|
def normalize_resume_output_dir(path_value: str) -> str:
|
|
path = resolve_output_dir(path_value)
|
|
if not _is_under_outputs(path):
|
|
raise ValueError("Resume checkpoint must be inside Unsloth outputs.")
|
|
return str(path)
|
|
|
|
|
|
def _run_config(run: dict) -> dict:
|
|
raw_config = run.get("config_json")
|
|
if isinstance(raw_config, dict):
|
|
return raw_config
|
|
if not isinstance(raw_config, str) or not raw_config.strip():
|
|
return {}
|
|
try:
|
|
parsed = json.loads(raw_config)
|
|
except (json.JSONDecodeError, TypeError):
|
|
return {}
|
|
return parsed if isinstance(parsed, dict) else {}
|
|
|
|
|
|
def _uses_s3_dataset(run: dict) -> bool:
|
|
config = _run_config(run)
|
|
return config.get("dataset_source") == "s3" or "s3_dataset" in config
|
|
|
|
|
|
def can_resume_run(run: dict) -> bool:
|
|
if run.get("resumed_later"):
|
|
return False
|
|
if _uses_s3_dataset(run):
|
|
return False
|
|
|
|
final_step = run.get("final_step")
|
|
total_steps = run.get("total_steps")
|
|
has_remaining_steps = (
|
|
not isinstance(final_step, int)
|
|
or not isinstance(total_steps, int)
|
|
or total_steps <= 0
|
|
or final_step < total_steps
|
|
)
|
|
return (
|
|
run.get("status") == "stopped"
|
|
and has_remaining_steps
|
|
and has_resume_state(run.get("output_dir"))
|
|
)
|