README.md

README.md

@@ -59,7 +59,6 @@ This model serves as the **core component** of a full-stack **AI engineering and
 | **Method** | QLoRA (Quantized LoRA Fine-Tuning) |
 | **Language** | English only |
 | **Precision** | 4-bit (NF4) |
-| **LoRA Config** | r=16, alpha=32, Dropout=0.07 |
 | **Optimizer** | Paged AdamW 8-bit |
 | **Frameworks** | `transformers`, `peft`, `bitsandbytes`, `fastapi` |
 
@@ -94,8 +93,7 @@ This repository demonstrates how to integrate this adapter with:
 
 The fine tuning consist of multiple stage experiment
 
-Stage 1:
-
+#### Stage 1:
 | Phase | Summary | Runtime |
 |--------|----------|----------|
 | **1A** | Initial fine-tune (canceled due to overfitting) | 11h 50m |
@@ -104,12 +102,13 @@ Stage 1:
 | **1D / 1D-A / 1E** | Refinement attempts with packing & oversampling | ~3d total |
 | **1F** | Final adapter re-train from **1B** (expanded persona dataset, balanced oversampling) | 1d 5h |
 
-Stage 2:
+#### Stage 2:
+
 After gathering all the insights from the initial experiments (1A-1F), fine-tuning was restarted completely from scratch. By applying all the lessons learned, this new training process achieved better and more balanced performance in just 1s 21h.
 The adapter released in this repository is the result of this final, optimized training.
 | Phase | Summary | Runtime |
 |--------|----------|----------|
-| **1** | Fine-tune again from scratch by applying all the insights from previous experiments. | 1d 21h |
+| **1** | Fine-tune again from scratch(from base model) by applying all the insights from previous experiments. | 1d 21h |
 
 📊 **W&B Log (Phase 1F):** [wandb.ai/VoidNova/.../runs/bpju3d09](https://wandb.ai/VoidNova/phi-2-2.7B_qlora_alpaca-51.8k_identity-model-232_squadv2-15k/runs/bpju3d09?nw=nwuseradhafajp)
 📊 **W&B Log (Final):** [wandb.ai/VoidNova/.../runs/rx5fih5v](https://wandb.ai/VoidNova/phi-2_qlora_ZeroChat/runs/rx5fih5v?nw=nwuseradhafajp)