Commit Graph

2 Commits

Author SHA1 Message Date
张宗平 8aeddebce9 test(m4): instruct_check unit tests + unbuffered training scripts
- tests/test_instruct_check.py: cover load_by_category (bucketing/cap/seed
  determinism/short-pool/blank-line) and _forecast_list (nested/flat/
  dict/garbage). 8 tests pass.
- train_stage{1,2}.sh: export PYTHONPATH=src + PYTHONUNBUFFERED=1 so future
  background runs stream logs live (current stage2 run is block-buffered).
2026-06-30 07:27:03 +00:00
张宗平 357e2e60bd feat(m4): stage 2 SFT training script (LoRA r=16) + smoke (T4.1)
- src/tsmm/train/stage2.py: loads stage1 ckpt (optional), freeze_llm +
  enable_lora(r=16) on q/v_proj, masked LM loss on sft.jsonl, bs=4/grad_accum=8/
  ctx=1024/BF16/gradient checkpointing, ckpt every 2000 steps (encoder+projector
  state + peft LoRA adapter via save_pretrained).
- scripts/train_stage2.sh: wrapper with design defaults.
- Smoke verified: --max_steps 4, LoRA injected, finite loss, peak 3.29 GB
  (≤11GB budget), ckpt+adapter saved.
2026-06-30 03:11:00 +00:00