feat(compressors): add JSONL training metrics logging with CLI controls

- 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.

pyproject.toml

@@ -22,6 +22,9 @@ dependencies = [
     "scikit-learn>=1.7.2",
     "transformers>=5.0.0",
     "typer>=0.24.1",
+    "torch==2.7.1",
+    "torchvision==0.22.1",
+    "torchaudio==2.7.1",
 ]
 
 [dependency-groups]
@@ -38,6 +41,23 @@ dev = [
     "cocotb-tools>=0.1.0",
 ]
 
+[[tool.uv.index]]
+name = "pytorch-cu128"
+url = "https://download.pytorch.org/whl/cu128"
+explicit = true
+
+[tool.uv.sources]
+torch = [
+  { index = "pytorch-cu128", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
+]
+torchvision = [
+  { index = "pytorch-cu128", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
+]
+torchaudio = [
+    { index = "pytorch-cu128", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
+]
+
+
 [tool.ty.environment]
 python = "$UV_PROJECT_ENVIRONMENT"
 root = ["./mini-nav", "./notebooks", "./hw/sim", "./scripts"]