mirror of
https://github.com/SikongJueluo/Mini-Nav.git
synced 2026-07-13 04:25:32 +08:00
- Add write_training_metrics() in new compressors/training_metrics.py for appending epoch/step/lr/component rows as JSON Lines - Wire --metrics-path and --log-every CLI options into train.py, passing them to the training loop so metrics rows are written every N steps - Accept absolute metrics paths or paths relative to output directory - Add quantization component to loss log alongside existing distill/contrastive - Replace inline torch.device() with get_device() utility - Add test_hash_training_metrics.py covering multi-row JSONL append Infrastructure: - Pin torch 2.7.1 + CUDA 12.8 index for Linux/Windows in pyproject.toml - Add .justfile rsync upload recipe with .stignore exclusion - Exclude **/__marimo__ from rsync in .stignore Dependencies updated: numpy 2.4.5, pandas 3.0.3, black 26.5.0, click 8.4.0, contourpy, etc.
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
import typer
|
|
from commands import app
|
|
|
|
|
|
@app.command()
|
|
def train(
|
|
ctx: typer.Context,
|
|
epoch_size: int = typer.Option(10, "--epoch", "-e", help="Number of epochs"),
|
|
batch_size: int = typer.Option(64, "--batch", "-b", help="Batch size"),
|
|
lr: float = typer.Option(1e-4, "--lr", "-l", help="Learning rate"),
|
|
checkpoint_path: str = typer.Option(
|
|
"hash_checkpoint.pt", "--checkpoint", "-c", help="Checkpoint path"
|
|
),
|
|
metrics_path: str = typer.Option(
|
|
"hash_training_metrics.jsonl",
|
|
"--metrics-path",
|
|
"-m",
|
|
help="JSONL metrics path for loss curves; relative to output directory unless absolute",
|
|
),
|
|
log_every: int = typer.Option(
|
|
1,
|
|
"--log-every",
|
|
help="Write one metrics row every N global steps; <=0 disables metrics logging",
|
|
),
|
|
):
|
|
from compressors import train as train_module
|
|
|
|
train_module(
|
|
epoch_size=epoch_size,
|
|
batch_size=batch_size,
|
|
lr=lr,
|
|
checkpoint_path=checkpoint_path,
|
|
metrics_path=metrics_path,
|
|
log_every=log_every,
|
|
)
|