Update README.md

README.md

@@ -36,17 +36,17 @@ GPT-OSS-20B Base Model
 │    ├─ Layers: MLP + Attention
 │    └─ Goal: Establish coding + reasoning foundation
 │
-├─── Phase 1.5: Knowledge Consolidation (Week 5)
+├─── Phase 1.5: Knowledge Consolidation
 │    ├─ Data: Mixed replay of Phase 1 data
 │    ├─ Layers: MLP + Attention
 │    └─ Goal: Prevent early forgetting
 │
-├─── Phase 2: Specialization Training (Weeks 6-8)
+├─── Phase 2: Specialization Training
 │    ├─ Data: Claude Sonnet (250) + GPT-5.2 high (250) + Replay (150)
 │    ├─ Layers: MLP + Adapter
 │    └─ Goal: Integrate balanced reasoning + maintain coding
 │
-└─── Phase 2.5: Gradual Unfreezing (Week 8, Optional)
+└─── Phase 2.5: Gradual Unfreezing
      ├─ Data: Full mixed dataset
      ├─ Layers: Upper Attention layers + MLP + Adapter
      └─ Goal: Fine-tune attention patterns if needed