29 lines
2.9 KiB
Python
29 lines
2.9 KiB
Python
"""Audit recorded scope, metrics and reproducibility files; no model execution."""
|
||
import csv,json,hashlib
|
||
from pathlib import Path
|
||
import sys
|
||
p=Path(sys.argv[1]);r=list(csv.DictReader((p/'metrics.csv').open()));s=json.loads((p/'summary.json').read_text())
|
||
assert s['completed'] and len(r)==s['rows']==4*20904
|
||
assert len({x['sample'] for x in r})==4
|
||
assert {int(x['module'].split('.')[1]) for x in r}==set(range(24))
|
||
for x in r:
|
||
for k in ['zero_rate','negative_rate','near_001_rms','near_01_rms','ever_active_001','energy90_channel_fraction']:assert 0<=float(x[k])<=1,(x,k)
|
||
assert float(x['zero_rate'])<=float(x['near_001_rms'])<=float(x['near_01_rms'])
|
||
assert int(x['channels'])==int(x['stop'])-int(x['start'])
|
||
a=json.loads((p/'aggregates.json').read_text());lines=['# 实测激活率：SiLU 门控模型','', '覆盖24层、4条中英文文本，每条32 token；所有投影输出及 MLP 门控中间量，按64/128输出通道分块。','', '| 输出 | 精确零比例均值 | 0.01 RMS以下均值 | 0.1 RMS以下均值 | 32 token内曾活跃通道比例均值 | 90%能量所需通道比例均值 |','|---|---:|---:|---:|---:|---:|']
|
||
for k,v in a.items():
|
||
cols=[v[m]['mean']*100 for m in ['zero_rate','near_001_rms','near_01_rms','ever_active_001','energy90_channel_fraction']]
|
||
lines.append('| '+k+' | '+' | '.join(f'{z:.4f}%' for z in cols)+' |')
|
||
blocks=[x for x in r if x['width']=='128']; dead=sum(float(x['zero_rate'])==1 for x in blocks)
|
||
lines+=['',f'128通道块×文本观测共{len(blocks)}条，整个32 token窗口全为精确零的块观测数为{dead}。', '', '表中是整模块逐文本统计再取均值；每个分块的独立统计见 metrics.csv。阈值是各自RMS的比例；阈值下激活率=1−近零比例。能量集中不等于可删除或可替换。', '', '仅测该模型、四条短文本；不推断所有语言/长上下文。SiLU不把负值整体截零，负数不等于静默。未执行删块/跳算的质量验证。权重和既有缓存全部保留。', '',f"CPU测量耗时{s['elapsed_seconds']:.1f}秒，峰值RSS{s['peak_rss_kib']/1024:.1f} MiB。"]
|
||
(p/'REPORT.md').write_text('\n'.join(lines)+'\n')
|
||
lines_extra=[]
|
||
for suffix in ['mlp.gated_product','self_attn.q_proj.output','self_attn.k_proj.output','self_attn.v_proj.output']:
|
||
rr=[x for x in blocks if x['module'].endswith(suffix)]
|
||
act=sorted(1-float(x['near_01_rms']) for x in rr)
|
||
lines_extra.append(f'{suffix}: 128通道块在0.1 RMS阈值上的激活率范围 {100*act[0]:.2f}%–{100*act[-1]:.2f}%。')
|
||
with (p/'REPORT.md').open('a') as f:f.write('\n'+'\n'.join(lines_extra)+'\n')
|
||
(p/'audit.json').write_text(json.dumps({'passed':True,'rows':len(r),'layers':24,'samples':4,'all_zero_128_blocks':dead},indent=2))
|
||
files=[x for x in p.rglob('*') if x.is_file() and x.name!='checksums.json'];(p/'checksums.json').write_text(json.dumps({str(x.relative_to(p)):hashlib.sha256(x.read_bytes()).hexdigest() for x in sorted(files)},indent=2))
|
||
print((p/'REPORT.md').read_text())
|