-
V6.7: upload reports/v67_fase2_metrics.json (10.0KB) — FASE1+FASE2 training results
-
Delete reports/archive
-
V6.7: archive old reports (v6_4, v6_5_7ds_attn v1/v2/v3)
-
V7 FINAL: FASE1+FASE2 completed (10000 samples, 20 punishments)
V7 fixes:
- AdvancedSOMAugmenter.fit(): torch.no_grad() wrapper (OOM fix + .item() fix)
- V7Fase2Integrator.post_chunk_hook: defensive int/float, traceback logging
- V7Fase2Integrator._compute_adaptive_dpo: kls.neuron_label fix (was kls.som.neuron_labels)
- SimpleBBPETokenizer: pure alias to BBPETokenizer (no duplicate impl)
- train_v6_5_v2.py: SKIP_FASE1 support for FASE2 resume
Results:
- FASE1: 8000 samples (8 datasets, Kohonen only)
- FASE2: 2000 samples (BrunoN-Dev/corpus-ptbr-v1, punishment active)
- V7 augmenter: 10 fit() calls, 0 errors
- V7 DPO: 20 triggers, 0 errors
- SOM: dead 92.6%->56%, TE 0.87->0.39, VE 0.98
Cleanup:
- Deleted 1 misplaced/old files from HF root
- Uploaded 18 files to correct paths -
V6.5-V4-canonical-256: buffer=256 + grid=(4,4,4,4)=256 + BBPE serial fix
Mudanças principais:
- Buffer canônico 256 (alinhado ao grid 256, elimina OOM de V6.5-V3)
- BBPE serial in-process para corpus < 200 textos (evita OOM por ProcessPoolExecutor)
- FASE1: 7000 samples processados (7/8 datasets)
- FASE2: 2000 samples com punição ativa (meta atingida)
- 23 punishment events, 11 hypotheses trainings, 11 delta applications
- Peak RSS: 1933MB (dentro do limite 4GB cgroup)
- Paths remapeados: TODOS módulos em src/bigru_t/**
- Sem duplicidade: deprecated/ NÃO enviados
Timestamp: 2026-08-09T18:18:20.529072 -
V6.5-V3-hyp-synergy: SynergyHypothesisEnsemble (4 pilares: diversidade k-means++, cooperação, competição, ortogonalidade) + testes de validação (7 files)
