mirror of
https://github.com/wassname/evil_MoE.git
synced 2026-07-19 11:23:21 +08:00
wassnameandClaudypoo
8249a9691e
The smoke prereqs (out/pools/substrate, out/pools/teacher_pool, out/vhack/v_hack_smoke) are gitignored pipeline outputs that only exist on the GPU box -- a fresh clone died at verify_partition.py on a FileNotFoundError for partition.json. Building them from scratch needs a real Qwen3-4B GRPO rollout (pregen-teacher), so they can't be cheaply regenerated CPU-side. Force-add them (~2.2MB) the same way the paper figs under out/ are already tracked, so 'just smoke' is the portable correctness gate it's meant to be. Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
38 lines
1.0 KiB
Markdown
38 lines
1.0 KiB
Markdown
# probe_distill report
|
|
|
|
|
|
|
|
*Rollout outcomes per training step for projected GRPO at seed=41. Schedule: 0 steps of student-generated rollouts, then None steps of replay-distillation from a saved teacher+base pool, then 20 steps of student-generated rollouts. Categories: correct (green), correct with attempted reward hack (yellow), reward hack (red), attempted reward hack (purple), incorrect (grey). Values are a 10-step trailing moving average. Dashed lines mark distillation on/off.*
|
|
|
|
## metadata
|
|
|
|
```json
|
|
{
|
|
"arm": "projected",
|
|
"seed": 41,
|
|
"tag": "teacher_pool",
|
|
"steps": 20,
|
|
"pre_warmup_steps": 0,
|
|
"warmup_replay_steps": null,
|
|
"group": 8,
|
|
"n_problems": 300,
|
|
"argv": [
|
|
"/workspace/projected_grpo/src/projected_grpo/probe_distill.py",
|
|
"--teacher-only",
|
|
"--n-problems=300",
|
|
"--group=8",
|
|
"--max-new=1024"
|
|
],
|
|
"pre": {
|
|
"hack": 0.98125,
|
|
"pass": 0.34375,
|
|
"n_steps": 20
|
|
},
|
|
"post": {
|
|
"hack": NaN,
|
|
"pass": NaN,
|
|
"n_steps": 0
|
|
}
|
|
}
|
|
```
|