| # ScriptSwiftAI v12 (Dikshan) | |
| > QLoRA fine-tuned full-stack code generation model by **Dikshan** (India). | |
| > Covers Python, Django, Flask, FastAPI, React, Next.js, TypeScript, SQL, Docker. | |
| --- | |
| ## License | |
| **CC BY-NC 4.0** — Non-commercial use only. Must credit Dikshan / ScriptSwiftAI. | |
| https://creativecommons.org/licenses/by-nc/4.0/ | |
| **Copyright © 2026 Dikshan. All rights reserved.** | |
| --- | |
| ## Model Details | |
| | Property | Value | | |
| |---|---| | |
| | **Base Model** | Qwen2.5-Coder-7B-Instruct | | |
| | **Method** | QLoRA (4-bit, r=64) | | |
| | **Hardware** | NVIDIA RTX 5070 Ti 16GB | | |
| | **Target Steps** | 40,000 | | |
| | **Dataset** | ~450-500k samples (17 datasets) | | |
| | **Max Length** | 1536 tokens | | |
| | **Developer** | Dikshan (India) | | |
| | **Training Started** | June 2026 | | |
| --- | |
| ## Changelog / Training Timeline | |
| *Auto-updated by train_v12.py on every checkpoint save.* | |
| *Append-only — entries never overwritten. HuggingFace commit history provides timestamps.* | |
| --- | |
| ### 🔵 Checkpoint — Step 13 | |
| **Date:** June 22, 2026 at 18:44 IST | |
| **Checkpoint:** checkpoint-13 | |
| **Step:** 13 / 40,000 (0.0% complete) | |
| **Loss:** 0.6164 | |
| **Epoch:** 0.000 | |
| **Zone:** 📚 Learning | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 25 | |
| **Date:** June 22, 2026 at 18:50 IST | |
| **Checkpoint:** checkpoint-25 | |
| **Step:** 25 / 40,000 (0.1% complete) | |
| **Loss:** 0.6057 | |
| **Epoch:** 0.001 | |
| **Zone:** 📚 Learning | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 36 | |
| **Date:** June 22, 2026 at 18:58 IST | |
| **Checkpoint:** checkpoint-36 | |
| **Step:** 36 / 40,000 (0.1% complete) | |
| **Loss:** 0.5508 | |
| **Epoch:** 0.001 | |
| **Zone:** 📚 Learning | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 42 | |
| **Date:** June 22, 2026 at 19:08 IST | |
| **Checkpoint:** checkpoint-42 | |
| **Step:** 42 / 40,000 (0.1% complete) | |
| **Loss:** 0.5525 | |
| **Epoch:** 0.001 | |
| **Zone:** 📚 Learning | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 538 | |
| **Date:** June 22, 2026 at 23:38 IST | |
| **Checkpoint:** checkpoint-538 | |
| **Step:** 538 / 40,000 (1.3% complete) | |
| **Loss:** 0.4087 | |
| **Epoch:** 0.015 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 1,000 | |
| **Date:** June 23, 2026 at 03:05 IST | |
| **Checkpoint:** checkpoint-1000 | |
| **Step:** 1,000 / 40,000 (2.5% complete) | |
| **Loss:** 0.4174 | |
| **Epoch:** 0.029 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 1,797 | |
| **Date:** June 23, 2026 at 08:26 IST | |
| **Checkpoint:** checkpoint-1797 | |
| **Step:** 1,797 / 40,000 (4.5% complete) | |
| **Loss:** 0.3927 | |
| **Epoch:** 0.052 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 2,000 | |
| **Date:** June 23, 2026 at 09:52 IST | |
| **Checkpoint:** checkpoint-2000 | |
| **Step:** 2,000 / 40,000 (5.0% complete) | |
| **Loss:** 0.4383 | |
| **Epoch:** 0.058 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 3,000 | |
| **Date:** June 23, 2026 at 17:35 IST | |
| **Checkpoint:** checkpoint-3000 | |
| **Step:** 3,000 / 40,000 (7.5% complete) | |
| **Loss:** 0.4153 | |
| **Epoch:** 0.088 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 3,876 | |
| **Date:** June 23, 2026 at 23:40 IST | |
| **Checkpoint:** checkpoint-3876 | |
| **Step:** 3,876 / 40,000 (9.7% complete) | |
| **Loss:** 0.3439 | |
| **Epoch:** 0.113 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 4,000 | |
| **Date:** June 24, 2026 at 00:54 IST | |
| **Checkpoint:** checkpoint-4000 | |
| **Step:** 4,000 / 40,000 (10.0% complete) | |
| **Loss:** 0.3980 | |
| **Epoch:** 0.117 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 5,000 | |
| **Date:** June 24, 2026 at 07:38 IST | |
| **Checkpoint:** checkpoint-5000 | |
| **Step:** 5,000 / 40,000 (12.5% complete) | |
| **Loss:** 0.2748 | |
| **Epoch:** 0.146 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 6,000 | |
| **Date:** June 24, 2026 at 14:22 IST | |
| **Checkpoint:** checkpoint-6000 | |
| **Step:** 6,000 / 40,000 (15.0% complete) | |
| **Loss:** 0.2319 | |
| **Epoch:** 0.175 | |
| **Zone:** 🎯 Sweet Spot | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 6,326 | |
| **Date:** June 24, 2026 at 19:59 IST | |
| **Checkpoint:** checkpoint-6326 | |
| **Step:** 6,326 / 40,000 (15.8% complete) | |
| **Loss:** 0.2695 | |
| **Epoch:** 0.185 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 6,739 | |
| **Date:** June 24, 2026 at 23:37 IST | |
| **Checkpoint:** checkpoint-6739 | |
| **Step:** 6,739 / 40,000 (16.8% complete) | |
| **Loss:** 0.1934 | |
| **Epoch:** 0.197 | |
| **Zone:** 🎯 Sweet Spot | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 7,000 | |
| **Date:** June 25, 2026 at 02:24 IST | |
| **Checkpoint:** checkpoint-7000 | |
| **Step:** 7,000 / 40,000 (17.5% complete) | |
| **Loss:** 0.1105 | |
| **Epoch:** 0.205 | |
| **Zone:** ⚠️ Overfit Risk | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 8,000 | |
| **Date:** June 25, 2026 at 09:05 IST | |
| **Checkpoint:** checkpoint-8000 | |
| **Step:** 8,000 / 40,000 (20.0% complete) | |
| **Loss:** 0.2105 | |
| **Epoch:** 0.234 | |
| **Zone:** 🎯 Sweet Spot | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 8,978 | |
| **Date:** June 25, 2026 at 15:38 IST | |
| **Checkpoint:** checkpoint-8978 | |
| **Step:** 8,978 / 40,000 (22.4% complete) | |
| **Loss:** 0.3111 | |
| **Epoch:** 0.262 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 9,000 | |
| **Date:** June 25, 2026 at 15:47 IST | |
| **Checkpoint:** checkpoint-9000 | |
| **Step:** 9,000 / 40,000 (22.5% complete) | |
| **Loss:** 0.3143 | |
| **Epoch:** 0.263 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 9,090 | |
| **Date:** June 25, 2026 at 16:29 IST | |
| **Checkpoint:** checkpoint-9090 | |
| **Step:** 9,090 / 40,000 (22.7% complete) | |
| **Loss:** 0.3586 | |
| **Epoch:** 0.266 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 9,718 | |
| **Date:** June 25, 2026 at 21:33 IST | |
| **Checkpoint:** checkpoint-9718 | |
| **Step:** 9,718 / 40,000 (24.3% complete) | |
| **Loss:** 0.2998 | |
| **Epoch:** 0.284 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 9,942 | |
| **Date:** June 25, 2026 at 23:59 IST | |
| **Checkpoint:** checkpoint-9942 | |
| **Step:** 9,942 / 40,000 (24.9% complete) | |
| **Loss:** 0.2736 | |
| **Epoch:** 0.291 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 10,000 | |
| **Date:** June 26, 2026 at 00:23 IST | |
| **Checkpoint:** checkpoint-10000 | |
| **Step:** 10,000 / 40,000 (25.0% complete) | |
| **Loss:** 0.2685 | |
| **Epoch:** 0.292 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 11,000 | |
| **Date:** June 26, 2026 at 07:17 IST | |
| **Checkpoint:** checkpoint-11000 | |
| **Step:** 11,000 / 40,000 (27.5% complete) | |
| **Loss:** 0.4008 | |
| **Epoch:** 0.322 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 12,000 | |
| **Date:** June 26, 2026 at 14:10 IST | |
| **Checkpoint:** checkpoint-12000 | |
| **Step:** 12,000 / 40,000 (30.0% complete) | |
| **Loss:** 0.3562 | |
| **Epoch:** 0.351 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 12,694 | |
| **Date:** June 26, 2026 at 19:36 IST | |
| **Checkpoint:** checkpoint-12694 | |
| **Step:** 12,694 / 40,000 (31.7% complete) | |
| **Loss:** 0.3882 | |
| **Epoch:** 0.371 | |
| **Zone:** 📈 Good | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 12,793 | |
| **Date:** June 26, 2026 at 20:50 IST | |
| **Checkpoint:** checkpoint-12793 | |
| **Step:** 12,793 / 40,000 (32.0% complete) | |
| **Loss:** 0.2054 | |
| **Epoch:** 0.374 | |
| **Zone:** 🎯 Sweet Spot | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |
| --- | |
| ### 🔵 Checkpoint — Step 13,000 | |
| **Date:** June 26, 2026 at 22:14 IST | |
| **Checkpoint:** checkpoint-13000 | |
| **Step:** 13,000 / 40,000 (32.5% complete) | |
| **Loss:** 0.2178 | |
| **Epoch:** 0.380 | |
| **Zone:** 🎯 Sweet Spot | |
| **Status:** Training ongoing — auto-uploaded via train_v12.py | |