Spaces:
Sleeping
Sleeping
File size: 4,023 Bytes
d63a1ba | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | """Run the full resumable local LoRA pipeline."""
from __future__ import annotations
import argparse
import json
import subprocess
import sys
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
if str(ROOT) not in sys.path:
sys.path.insert(0, str(ROOT))
from training_utils import latest_checkpoint, write_json
def run_step(name: str, command: list[str], log_path: Path, output_root: Path) -> None:
log_path.parent.mkdir(parents=True, exist_ok=True)
with log_path.open("a", encoding="utf-8") as log_handle:
log_handle.write(f"\n===== {name} =====\n")
log_handle.flush()
write_json(
output_root / "run_manifest.json",
{
"status": "running_step",
"current_step": name,
"command": command,
"latest_checkpoint": str(latest_checkpoint(output_root / "checkpoints")) if (output_root / "checkpoints").exists() else None,
},
)
process = subprocess.run(command, stdout=log_handle, stderr=subprocess.STDOUT, text=True)
if process.returncode != 0:
raise SystemExit(process.returncode)
def main() -> None:
parser = argparse.ArgumentParser()
parser.add_argument("--model", default="Qwen/Qwen3.5-4B")
parser.add_argument("--output-root", default="artifacts/lora_qwen3_4b")
parser.add_argument("--augmentations", type=int, default=12)
parser.add_argument("--skip-base-eval", action="store_true")
args = parser.parse_args()
output_root = (ROOT / args.output_root).resolve()
logs_dir = output_root / "logs"
output_root.mkdir(parents=True, exist_ok=True)
if not args.skip_base_eval and not (output_root / "metrics" / "eval_before.json").exists():
run_step(
"eval_base",
[
sys.executable,
"scripts/evaluate_lora.py",
"--model",
args.model,
"--output-root",
str(output_root),
"--output-json",
str(output_root / "metrics" / "eval_before.json"),
],
logs_dir / "eval_base.log",
output_root,
)
if not (output_root / "data" / "train.jsonl").exists():
run_step(
"generate_data",
[
sys.executable,
"scripts/generate_sft_data.py",
"--output-root",
str(output_root),
"--augmentations",
str(args.augmentations),
],
logs_dir / "generate_data.log",
output_root,
)
run_step(
"train_lora",
[
sys.executable,
"scripts/train_lora_sft.py",
"--model",
args.model,
"--output-root",
str(output_root),
],
logs_dir / "train_lora.log",
output_root,
)
run_step(
"eval_adapter",
[
sys.executable,
"scripts/evaluate_lora.py",
"--model",
args.model,
"--adapter-path",
str(output_root / "adapter"),
"--output-root",
str(output_root),
"--output-json",
str(output_root / "metrics" / "eval_after.json"),
],
logs_dir / "eval_adapter.log",
output_root,
)
write_json(
output_root / "run_manifest.json",
{
"status": "finished",
"output_root": str(output_root),
"eval_before": str(output_root / "metrics" / "eval_before.json"),
"training_summary": str(output_root / "training_summary.json"),
"eval_after": str(output_root / "metrics" / "eval_after.json"),
},
)
print(
json.dumps(
{
"status": "finished",
"output_root": str(output_root),
},
indent=2,
)
)
if __name__ == "__main__":
main()
|