QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)
Browse files- HANDOVER.md +37 -1
- ops/v5_daemon.py +19 -2
- ops/v5_round.py +127 -0
HANDOVER.md
CHANGED
|
@@ -10,6 +10,29 @@
|
|
| 10 |
通过信封逐帧看画面、逐步发动作 → 轨迹直写 collect_selfplay 兼容 schema(标签=教师动作,
|
| 11 |
天然 BC)→ `ops/v5_daemon.py` 每 10min 快照轨迹→重建数据集→续训 40 步→上传 HF(HEAD 验证)。
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
**v5t gen-1 已完成并归档**:68 步 ar25 教学 → 66 choice/67 boolean/68 score 样本 →
|
| 14 |
从 v4b 续训(v0.4.13 新补丁:out_dir 已有 qwenjev_s1.pt 则 load_heads 续接)→ 40 步 →
|
| 15 |
全产物 HEAD 验证在 HF `t4_assets_v5/checkpoints/`。训练判读:choice loss 前段≈0
|
|
@@ -273,7 +296,20 @@ python qwenjev/ops/t4exec.py runfile <本地.py> # 执行本地脚本(内含
|
|
| 273 |
|
| 274 |
## 6. 下一步(按优先级)
|
| 275 |
|
| 276 |
-
0. **【进行中 2026-09-24】
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 277 |
teach_server + daemon 架构见 §0;VIK9H6GV 会话产出 gen-1/2/3/4 代际
|
| 278 |
(HEAD 200)。**教学工具链(本地 scripts/t4/)**:teach_step.sh(单信封
|
| 279 |
单步:写 cmd→睡→取 obs→渲染)、watch.sh(紧凑几何摘要)、t4r.py(重试
|
|
|
|
| 10 |
通过信封逐帧看画面、逐步发动作 → 轨迹直写 collect_selfplay 兼容 schema(标签=教师动作,
|
| 11 |
天然 BC)→ `ops/v5_daemon.py` 每 10min 快照轨迹→重建数据集→续训 40 步→上传 HF(HEAD 验证)。
|
| 12 |
|
| 13 |
+
**【现行权威 2026-09-24】0S3BN0UN 会话(T4X2, 12h 窗)—— L1/L2 通关配方重放成功 + L3 机制图半解**:
|
| 14 |
+
① 本会话(游戏版 0c5556536)L1/L2 布局与旧会话不同(初始列位置随机化),但摆钟语法一致:
|
| 15 |
+
**L1 配方(17 步)**:A4→A3×6(4 塔 33-41→51-59 对位蓝图)→A2×10(全体+3 下行入槽)→WIN;
|
| 16 |
+
**L2 配方(24 步)**:A4×3(墙+9/press 扫过 4 塔触发世界重组)→A5(钻孔)→A2×8
|
| 17 |
+
(全体+3 降至蓝图行带)→A5→A3×6(4 脚手架 -6/press 行军拼装镜像 S 模具覆盖蓝图)→WIN;
|
| 18 |
+
② L2 语义图:A1=全体↑3/A2=全体↓3/A3=重排·左(5 件 −3,4 脚手架重组)/
|
| 19 |
+
A4=重排·右(世界相位 +3,4→5 转换+穿孔)/**A5=钻孔机+搬0**(pit 在墙轴↔件内 lattice 间搬运,
|
| 20 |
+
0 门恒在 rows≡1 mod3 × cols≡1 mod3)/**A7=免费 UNDO(撤销上一步,无风险实验钥匙)**/A6=惰性;
|
| 21 |
+
③ **L3 机制图(半解,~40 步实证)**:开局对称双塔(4 左 5 右,b 窗=晶格点);A3 一按重组为
|
| 22 |
+
水平墙+5 件套上半场+b 模具下半场;A1/A2=墙升降机(**墙停处门区烙 b = 行走蓝图打印机**);
|
| 23 |
+
A5=铸造扳机(板内 lattice 钻孔 + 模具区材料化 4 柱);**墙=移动浇铸机**(身后浇铸
|
| 24 |
+
5 板垂直翻转的 4 复制品,随墙移动旧品蒸发);A2 亦可触发垂直色/形置换;
|
| 25 |
+
目标判定:4 复制品精确覆盖 b 模具(同 L1/L2 判据族)。
|
| 26 |
+
④ 部署/训练坑(本会话实录):seed 块静默失败(中继吞响应+大下载被杀)→ **必须远端文件实证**;
|
| 27 |
+
torchao 0.10.0 不满足 peft 0.19.1(需 ≥0.16)+ **坑 14 变体:exec 同进程 sys.modules 缓存
|
| 28 |
+
旧模块,pip 装完 import 仍见旧版** → 用子进程验证;手动训练轮 runner `ops/v5_round.py`
|
| 29 |
+
(分离进程,RESULT 逐条落盘 /content/v5_round.log)。
|
| 30 |
+
|
| 31 |
+
历史会话(VIK9H6GV)的塔式电梯地图见 §6 0.5;其 L1/L2 布局与现行版本不同,仅作参考。
|
| 32 |
+
|
| 33 |
+
**v5t 学生代际链(现行)**:gen1(181步)→gen2(240步) 已上链 t4_assets_v5/checkpoints/(HEAD 200);
|
| 34 |
+
0S3BN0UN 会话续教至 350+ 步(含 L1/L2 两个 WIN 正样本),gen3 训练轮(326 步数据集)进行中。
|
| 35 |
+
|
| 36 |
**v5t gen-1 已完成并归档**:68 步 ar25 教学 → 66 choice/67 boolean/68 score 样本 →
|
| 37 |
从 v4b 续训(v0.4.13 新补丁:out_dir 已有 qwenjev_s1.pt 则 load_heads 续接)→ 40 步 →
|
| 38 |
全产物 HEAD 验证在 HF `t4_assets_v5/checkpoints/`。训练判读:choice loss 前段≈0
|
|
|
|
| 296 |
|
| 297 |
## 6. 下一步(按优先级)
|
| 298 |
|
| 299 |
+
0. **【进行中 2026-09-24 傍晚】0S3BN0UN 会话(T4X2 Kaggle 2×T4, 12h 窗口)增量**:
|
| 300 |
+
- **L1/L2 通关配方重放成功**(见 §0 现行权威块),trace 已含两关 WIN 正样本
|
| 301 |
+
(291 步快照 HEAD 200;教学继续至 350+ 步)。
|
| 302 |
+
- **gen3 训练轮**:326 步数据集(choice 320/bool 325/score 326)训练中
|
| 303 |
+
(torchao==0.18.0 修复后)。完成判据:/content/v5_round.log 出现 ROUND DONE
|
| 304 |
+
+ HEAD ok 两行。**后续每 ~40 新教学步跑一轮 v5_round.py**。
|
| 305 |
+
- **L3 攻坚中**(机制图半解见 §0③):当前形态=两座复合塔+b 模具;
|
| 306 |
+
待试:墙降到模具行触发浇铸入位 / A5×N 连续铸造 / 复合塔 marching 对齐 12-14 列系。
|
| 307 |
+
- 待办队列:gen3 完成验证→gen3 评测(ar25@150 对照 v4b 0关0重置)→继续 L3
|
| 308 |
+
→bp35@150 随机基线补跑(`ops/random_baseline_runfile.py` 改 `[('bp35',150)]`)。
|
| 309 |
+
- 新工具:`ops/v5_round.py`(手动训练轮,daemon 冻结时的可靠替代);
|
| 310 |
+
部署脚本已改 gen2 种子(t4_assets_v5)+trace 先恢复后播种(防覆盖)。
|
| 311 |
+
|
| 312 |
+
0.5. **【历史】VIK9H6GV 会话产出 gen-1/2/3/4 代际(HEAD 200)**:
|
| 313 |
teach_server + daemon 架构见 §0;VIK9H6GV 会话产出 gen-1/2/3/4 代际
|
| 314 |
(HEAD 200)。**教学工具链(本地 scripts/t4/)**:teach_step.sh(单信封
|
| 315 |
单步:写 cmd→睡→取 obs→渲染)、watch.sh(紧凑几何摘要)、t4r.py(重试
|
ops/v5_daemon.py
CHANGED
|
@@ -23,7 +23,7 @@ sys.path.insert(0, '/content/qwenjev')
|
|
| 23 |
REPO = 'tchbcb/qwenjev'
|
| 24 |
OUT = '/content/qwenjev/checkpoints/qwenjev-s1-hf-v5t'
|
| 25 |
TRACES = '/content/teach'
|
| 26 |
-
CYCLE_SECONDS =
|
| 27 |
MIN_NEW_STEPS = 15 # skip cycle if the teacher added fewer steps
|
| 28 |
STEPS_PER_CYCLE = 25 # bounded GPU budget (~8-12 min at 30s/step)
|
| 29 |
TOKEN_FILE = '/content/qwenjev_work_v3/.hf_token'
|
|
@@ -74,6 +74,20 @@ def _lora_pt_name():
|
|
| 74 |
def upload_generation():
|
| 75 |
from huggingface_hub import HfApi
|
| 76 |
api = HfApi(token=hf_token())
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
uploads = [
|
| 78 |
(OUT + '/qwenjev_s1.pt', 't4_assets_v5/checkpoints/qwenjev_s1.pt'),
|
| 79 |
(_lora_pt_name(), 't4_assets_v5/checkpoints/hf_lora/adapter_model.pt'),
|
|
@@ -138,7 +152,10 @@ def main():
|
|
| 138 |
last = count_steps()
|
| 139 |
cycle = 0
|
| 140 |
while True:
|
| 141 |
-
time.sleep(
|
|
|
|
|
|
|
|
|
|
| 142 |
now = count_steps()
|
| 143 |
if now - last < MIN_NEW_STEPS:
|
| 144 |
log('cycle %d skipped: only +%d new steps' % (cycle, now - last))
|
|
|
|
| 23 |
REPO = 'tchbcb/qwenjev'
|
| 24 |
OUT = '/content/qwenjev/checkpoints/qwenjev-s1-hf-v5t'
|
| 25 |
TRACES = '/content/teach'
|
| 26 |
+
CYCLE_SECONDS = 300 # 5 min — teacher plays continuously
|
| 27 |
MIN_NEW_STEPS = 15 # skip cycle if the teacher added fewer steps
|
| 28 |
STEPS_PER_CYCLE = 25 # bounded GPU budget (~8-12 min at 30s/step)
|
| 29 |
TOKEN_FILE = '/content/qwenjev_work_v3/.hf_token'
|
|
|
|
| 74 |
def upload_generation():
|
| 75 |
from huggingface_hub import HfApi
|
| 76 |
api = HfApi(token=hf_token())
|
| 77 |
+
# iron law #7: the INSTANCE can die any second — teaching traces are the
|
| 78 |
+
# irreplaceable asset, push them EVERY generation before anything else
|
| 79 |
+
try:
|
| 80 |
+
import tarfile
|
| 81 |
+
tb = '/content/teach_traces_snapshot.tgz'
|
| 82 |
+
with tarfile.open(tb, 'w:gz') as t:
|
| 83 |
+
for f in sorted(glob.glob(TRACES + '/trace_teach_*.jsonl')):
|
| 84 |
+
t.add(f, arcname=os.path.basename(f))
|
| 85 |
+
api.upload_file(path_or_fileobj=tb,
|
| 86 |
+
path_in_repo='t4_assets_v5/traces/teach_traces.tgz',
|
| 87 |
+
repo_id=REPO)
|
| 88 |
+
log('traces snapshot uploaded (%d files)' % len(glob.glob(TRACES + '/trace_teach_*.jsonl')))
|
| 89 |
+
except Exception as exc:
|
| 90 |
+
log('traces snapshot FAILED (non-fatal): %r' % exc)
|
| 91 |
uploads = [
|
| 92 |
(OUT + '/qwenjev_s1.pt', 't4_assets_v5/checkpoints/qwenjev_s1.pt'),
|
| 93 |
(_lora_pt_name(), 't4_assets_v5/checkpoints/hf_lora/adapter_model.pt'),
|
|
|
|
| 152 |
last = count_steps()
|
| 153 |
cycle = 0
|
| 154 |
while True:
|
| 155 |
+
# pit 15: a bare time.sleep(300) silently freezes in the Kaggle
|
| 156 |
+
# sandbox (observed twice) — sleep in short slices instead
|
| 157 |
+
for _ in range(CYCLE_SECONDS // 5):
|
| 158 |
+
time.sleep(5)
|
| 159 |
now = count_steps()
|
| 160 |
if now - last < MIN_NEW_STEPS:
|
| 161 |
log('cycle %d skipped: only +%d new steps' % (cycle, now - last))
|
ops/v5_round.py
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""One-shot manual v5 training round (daemon-free, Kaggle-safe).
|
| 3 |
+
|
| 4 |
+
Run detached on T4: writes /content/v5_round.log with RESULT lines.
|
| 5 |
+
Steps: snapshot teach traces -> build dataset -> continue-train -> upload gen.
|
| 6 |
+
"""
|
| 7 |
+
import glob
|
| 8 |
+
import json
|
| 9 |
+
import os
|
| 10 |
+
import shutil
|
| 11 |
+
import subprocess
|
| 12 |
+
import sys
|
| 13 |
+
import tarfile
|
| 14 |
+
import time
|
| 15 |
+
|
| 16 |
+
sys.path.insert(0, '/content/qwenjev')
|
| 17 |
+
|
| 18 |
+
REPO = 'tchbcb/qwenjev'
|
| 19 |
+
OUT = '/content/qwenjev/checkpoints/qwenjev-s1-hf-v5t'
|
| 20 |
+
TRACES = '/content/teach'
|
| 21 |
+
TOKEN_FILE = '/content/qwenjev_work_v3/.hf_token'
|
| 22 |
+
LOG = '/content/v5_round.log'
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
def log(msg):
|
| 26 |
+
line = '[round %s] %s' % (time.strftime('%H:%M:%S'), msg)
|
| 27 |
+
with open(LOG, 'a') as f:
|
| 28 |
+
f.write(line + '\n')
|
| 29 |
+
print(line, flush=True)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
def hf_token():
|
| 33 |
+
if os.path.exists(TOKEN_FILE):
|
| 34 |
+
return open(TOKEN_FILE).read().strip()
|
| 35 |
+
return os.environ.get('HF_TOKEN', '')
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
def main():
|
| 39 |
+
gen_tag = 'gen3'
|
| 40 |
+
log('ROUND START %s' % gen_tag)
|
| 41 |
+
n = sum(1 for f in glob.glob(TRACES + '/trace_teach_*.jsonl')
|
| 42 |
+
for _ in open(f) if _.strip())
|
| 43 |
+
log('RESULT trace_steps=%d' % n)
|
| 44 |
+
|
| 45 |
+
# 1) snapshot traces into the dataset dir
|
| 46 |
+
os.makedirs('/content/qwenjev/data/traces_teach', exist_ok=True)
|
| 47 |
+
for f in glob.glob('/content/qwenjev/data/traces_teach/ep*.jsonl'):
|
| 48 |
+
os.remove(f)
|
| 49 |
+
for i, src in enumerate(sorted(glob.glob(TRACES + '/trace_teach_*.jsonl'))):
|
| 50 |
+
game = os.path.basename(src).replace('trace_teach_', '').replace('.jsonl', '')
|
| 51 |
+
shutil.copyfile(src, '/content/qwenjev/data/traces_teach/ep%03d_%s.jsonl' % (i + 1, game))
|
| 52 |
+
log('traces snapshotted')
|
| 53 |
+
|
| 54 |
+
# 2) build dataset
|
| 55 |
+
r = subprocess.run(['python3', '-m', 'data.build_dataset', '--in',
|
| 56 |
+
'data/traces_teach', '--out', 'data/dataset_teach'],
|
| 57 |
+
cwd='/content/qwenjev', capture_output=True, text=True, timeout=600)
|
| 58 |
+
log('RESULT build_dataset ok=%s %s' % (r.returncode == 0, r.stdout.strip()[-100:]))
|
| 59 |
+
if r.returncode != 0:
|
| 60 |
+
log('STDERR ' + r.stderr[-300:])
|
| 61 |
+
return
|
| 62 |
+
|
| 63 |
+
# 3) fold hf_lora -> stage_a_lora if present (continuity)
|
| 64 |
+
src, dst = OUT + '/hf_lora', OUT + '/stage_a_lora'
|
| 65 |
+
if os.path.exists(src + '/adapter_model.pt'):
|
| 66 |
+
for f in ('adapter_model.pt', 'adapter_config.json'):
|
| 67 |
+
if os.path.exists(src + '/' + f):
|
| 68 |
+
shutil.copyfile(src + '/' + f, dst + '/' + f)
|
| 69 |
+
shutil.copyfile(dst + '/adapter_model.pt', dst + '/adapter_model.safetensors')
|
| 70 |
+
log('lora folded hf_lora->stage_a_lora')
|
| 71 |
+
|
| 72 |
+
# 4) train
|
| 73 |
+
r = subprocess.run(['python3', '-u', '-B', 'train/train_system1.py',
|
| 74 |
+
'--config', 'configs/train_teach.yaml'],
|
| 75 |
+
cwd='/content/qwenjev', capture_output=True, text=True, timeout=3500)
|
| 76 |
+
tail = [l for l in r.stdout.splitlines() if 'step=' in l or 'done' in l.lower()]
|
| 77 |
+
for l in tail[-4:]:
|
| 78 |
+
log(' ' + l[:120])
|
| 79 |
+
log('RESULT trainer exit=%s' % r.returncode)
|
| 80 |
+
if r.returncode != 0:
|
| 81 |
+
log('STDERR ' + r.stderr[-400:])
|
| 82 |
+
return
|
| 83 |
+
|
| 84 |
+
# 5) upload generation
|
| 85 |
+
from huggingface_hub import HfApi
|
| 86 |
+
api = HfApi(token=hf_token())
|
| 87 |
+
try:
|
| 88 |
+
tb = '/content/teach_traces_snapshot.tgz'
|
| 89 |
+
with tarfile.open(tb, 'w:gz') as t:
|
| 90 |
+
for f in sorted(glob.glob(TRACES + '/trace_teach_*.jsonl')):
|
| 91 |
+
t.add(f, arcname=os.path.basename(f))
|
| 92 |
+
api.upload_file(path_or_fileobj=tb,
|
| 93 |
+
path_in_repo='t4_assets_v5/traces/teach_traces.tgz', repo_id=REPO)
|
| 94 |
+
log('RESULT traces uploaded')
|
| 95 |
+
except Exception as exc:
|
| 96 |
+
log('traces upload FAILED (non-fatal): %r' % exc)
|
| 97 |
+
d = OUT + '/hf_lora'
|
| 98 |
+
pt = d + '/adapter_model.pt'
|
| 99 |
+
st = d + '/adapter_model.safetensors'
|
| 100 |
+
if not os.path.exists(pt) and os.path.exists(st):
|
| 101 |
+
shutil.copyfile(st, pt)
|
| 102 |
+
uploads = [
|
| 103 |
+
(OUT + '/qwenjev_s1.pt', 't4_assets_v5/checkpoints/qwenjev_s1.pt'),
|
| 104 |
+
(pt, 't4_assets_v5/checkpoints/hf_lora/adapter_model.pt'),
|
| 105 |
+
(d + '/adapter_config.json', 't4_assets_v5/checkpoints/hf_lora/adapter_config.json'),
|
| 106 |
+
(OUT + '/stage_b_meta.json', 't4_assets_v5/checkpoints/stage_b_meta.json'),
|
| 107 |
+
]
|
| 108 |
+
for local, remote in uploads:
|
| 109 |
+
if not os.path.exists(local):
|
| 110 |
+
log('skip missing %s' % local)
|
| 111 |
+
continue
|
| 112 |
+
api.upload_file(path_or_fileobj=local, path_in_repo=remote, repo_id=REPO)
|
| 113 |
+
log('RESULT uploaded %s' % remote)
|
| 114 |
+
import urllib.request
|
| 115 |
+
for remote in ('t4_assets_v5/checkpoints/qwenjev_s1.pt',
|
| 116 |
+
't4_assets_v5/checkpoints/hf_lora/adapter_model.pt'):
|
| 117 |
+
url = 'https://huggingface.co/%s/resolve/main/%s' % (REPO, remote)
|
| 118 |
+
try:
|
| 119 |
+
resp = urllib.request.urlopen(urllib.request.Request(url, method='HEAD'))
|
| 120 |
+
log('RESULT HEAD ok %s (%s)' % (remote, resp.status))
|
| 121 |
+
except Exception as exc:
|
| 122 |
+
log('RESULT HEAD FAIL %s: %s' % (remote, exc))
|
| 123 |
+
log('ROUND DONE %s' % gen_tag)
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
if __name__ == '__main__':
|
| 127 |
+
main()
|